© 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. 7-RESID-POST-AA
    11. 32425
    Prev
    Next
    INDEX
    Explanations

    Mutation

    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
    ilk
    -0.07
    .Fore
    -0.06
    785
    -0.06
     особ
    -0.06
    800
    -0.06
    orado
    -0.06
    lein
    -0.06
    oline
    -0.06
    porte
    -0.06
    IDDLE
    -0.06
    POSITIVE LOGITS
     Mut
    0.16
     mutation
    0.13
    Mut
    0.13
    ut
    0.11
     mutations
    0.11
    mutable
    0.11
     mut
    0.11
     mutate
    0.10
     Mutation
    0.10
     mutated
    0.10
    Activations Density 0.011%

    No Known Activations