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. 129617
    Prev
    Next
    INDEX
    Explanations

    constraint

    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
     occasions
    -0.07
     Radio
    -0.07
     Fif
    -0.07
     urllib
    -0.07
     DFS
    -0.07
     Numbers
    -0.07
     Variety
    -0.07
     Pemb
    -0.07
     number
    -0.07
    _sock
    -0.07
    POSITIVE LOGITS
     constraints
    0.17
     Constraints
    0.13
     constraint
    0.12
     constrained
    0.11
    Constraint
    0.10
     constrain
    0.10
     Constraint
    0.10
    constraints
    0.09
    straints
    0.09
    ну
    0.08
    Activations Density 0.008%

    No Known Activations