© 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. 3-RESID-POST-AA
    11. 93953
    Prev
    Next
    INDEX
    Explanations

    bridge

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Concent
    -0.07
     seab
    -0.06
    .
    -0.06
     sectors
    -0.06
     quo
    -0.06
    ].
    -0.06
     Functor
    -0.06
     mostr
    -0.06
     Cous
    -0.06
    _coll
    -0.06
    POSITIVE LOGITS
     Bridge
    0.19
     bridge
    0.17
    橋
    0.08
    桥
    0.07
     міст
    0.07
     charming
    0.07
     bridges
    0.07
    amide
    0.07
    \Session
    0.07
    スター
    0.06
    Activations Density 0.008%

    No Known Activations