© 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. 30407
    Prev
    Next
    INDEX
    Explanations

    consistently

    np_max-act · gemini-2.0-flash

    the neuron flags decimal numbers or numeric values containing fractional parts.

    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
     เขต
    -0.06
     badly
    -0.06
     cena
    -0.06
     мал
    -0.06
    -area
    -0.06
    _live
    -0.06
     Schwar
    -0.06
     dried
    -0.06
    VECTOR
    -0.06
    048
    -0.06
    POSITIVE LOGITS
     consistently
    0.09
     очеред
    0.07
     obvyk
    0.07
    variably
    0.06
     Rob
    0.06
    OG
    0.06
     каждый
    0.06
     обо
    0.06
    olie
    0.06
     resilience
    0.06
    Activations Density 0.014%

    No Known Activations