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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129573
    Prev
    Next
    INDEX
    Explanations

    numbers and brackets

    np_max-act · gemini-2.0-flash

    The neuron is looking for in-text reference/citation markup (e.g. ref-type, supplementary, bib, sec, online tags).

    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
     meinen
    -0.06
    ันย
    -0.06
    亿元
    -0.06
    _ACC
    -0.06
    rename
    -0.06
    让我
    -0.06
    _root
    -0.06
     strr
    -0.06
    بین
    -0.06
     Yours
    -0.06
    POSITIVE LOGITS
     Creatures
    0.07
     dismissal
    0.06
     ⓘ
    0.06
     perc
    0.06
     UIImageView
    0.06
     tín
    0.06
    ucken
    0.06
     rendition
    0.06
     erotik
    0.06
     deal
    0.06
    Activations Density 0.002%

    No Known Activations