© 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. 7-RESID-POST-AA
    11. 32653
    Prev
    Next
    INDEX
    Explanations

    overly

    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
     استرات
    -0.07
    .onSubmit
    -0.07
    ریز
    -0.07
    Sem
    -0.07
     RTS
    -0.07
    aphore
    -0.07
     Hashtable
    -0.06
     contents
    -0.06
     процед
    -0.06
     EM
    -0.06
    POSITIVE LOGITS
     overly
    0.15
     dread
    0.07
    Wind
    0.07
    ledon
    0.06
    олее
    0.06
     Very
    0.06
     undue
    0.06
    jab
    0.06
    -area
    0.06
    über
    0.06
    Activations Density 0.002%

    No Known Activations