© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9147
    Prev
    Next
    INDEX
    Explanations

    time references

    np_max-act · gemini-2.0-flash

    references to significant events or actions related to corporate leadership transitions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects mentions of upcoming scheduled events or announcements (e.g. “press conference,” “next week,” “tomorrow”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hindi
    -0.07
    RDD
    -0.07
     metall
    -0.07
     competitors
    -0.06
     competitor
    -0.06
     geliyor
    -0.06
    (dr
    -0.06
     яй
    -0.06
     중요한
    -0.06
     csak
    -0.06
    POSITIVE LOGITS
     Fritz
    0.06
    (FALSE
    0.06
     tutorials
    0.06
    повід
    0.06
     Gest
    0.06
    )↵
    0.06
    .lineWidth
    0.06
    .calls
    0.06
     recount
    0.06
    nex
    0.06
    Activations Density 0.025%

    No Known Activations