© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 79174
    Prev
    Next
    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Buddha
    -0.06
     embraces
    -0.06
     민주
    -0.06
    amientos
    -0.06
     preempt
    -0.06
     intimacy
    -0.06
     regenerated
    -0.06
     treaties
    -0.06
     mistress
    -0.06
    _guard
    -0.06
    POSITIVE LOGITS
    rtype
    0.07
    -million
    0.07
    만
    0.07
     researched
    0.06
    bff
    0.06
    %m
    0.06
     heir
    0.06
    ,、
    0.06
    �
    0.06
    _WEB
    0.06
    Activations Density 0.058%

    No Known Activations