Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 39211
    Prev
    Next
    INDEX
    Explanations

    Code/data

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (sb
    -0.07
    BOOLEAN
    -0.07
    (nd
    -0.07
    _STR
    -0.06
    Had
    -0.06
    lobals
    -0.06
     hil
    -0.06
    _CHAN
    -0.06
    请输入
    -0.06
    -len
    -0.06
    POSITIVE LOGITS
     Metadata
    0.07
     Lage
    0.07
    ิการ
    0.07
    Scient
    0.07
     Rossi
    0.07
     astonished
    0.06
     Your
    0.06
    ItemImage
    0.06
     checkpoint
    0.06
    μενο
    0.06
    Activations Density 0.014%

    No Known Activations