Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52894
    Prev
    Next
    INDEX
    Explanations

    it

    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
    "To
    -0.06
    TEXT
    -0.06
    _solver
    -0.06
    otate
    -0.06
    -men
    -0.06
    巡
    -0.06
     Straight
    -0.06
    	↵		↵
    -0.06
    asd
    -0.06
    혼
    -0.06
    POSITIVE LOGITS
    Adv
    0.08
    .Service
    0.07
     orientation
    0.07
     výro
    0.07
    nila
    0.07
    ۲۹
    0.07
     spotlight
    0.06
     Bottle
    0.06
     downloader
    0.06
     مقاله
    0.06
    Activations Density 0.002%

    No Known Activations