© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 87981
    Prev
    Next
    INDEX
    Explanations

    graft

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gradients
    -0.07
     contexts
    -0.07
     Ferm
    -0.07
    .tail
    -0.06
     EventType
    -0.06
     dataIndex
    -0.06
    .Slice
    -0.06
     brackets
    -0.06
    MULT
    -0.06
    @media
    -0.06
    POSITIVE LOGITS
     theano
    0.07
    災
    0.07
    umbling
    0.06
     remed
    0.06
    植物
    0.06
     breathed
    0.06
    ointed
    0.06
    &D
    0.06
    �
    0.06
      
    0.06
    Activations Density 0.004%

    No Known Activations