© 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 (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 105026
    Prev
    Next
    INDEX
    Explanations

    TV shows renewal/cancellation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JLabel
    -0.06
     Peninsula
    -0.06
    lore
    -0.06
     GRA
    -0.06
     Rogue
    -0.06
     adore
    -0.06
    ###↵
    -0.06
     recherche
    -0.06
     scales
    -0.06
    munition
    -0.06
    POSITIVE LOGITS
    _commit
    0.08
     COMMON
    0.07
     سیستم
    0.06
    .ColumnName
    0.06
    �
    0.06
     NSMutableArray
    0.06
    _emb
    0.06
    _activ
    0.06
    gsub
    0.06
    _bc
    0.06
    Activations Density 0.004%

    No Known Activations