© 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. 19365
    Prev
    Next
    INDEX
    Explanations

    road, street

    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
    δας
    -0.07
    活
    -0.07
     تجربه
    -0.07
     fontSize
    -0.06
     JObject
    -0.06
    Ip
    -0.06
    .),
    -0.06
    мента
    -0.06
     diz
    -0.06
     dialogs
    -0.05
    POSITIVE LOGITS
    INSERT
    0.07
     wrestlers
    0.07
    River
    0.07
     مناطق
    0.06
     handguns
    0.06
     auss
    0.06
     implication
    0.06
     Nov
    0.06
    _insn
    0.06
    onents
    0.06
    Activations Density 0.001%

    No Known Activations