© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 127920
    Prev
    Next
    INDEX
    Explanations

    option

    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
    ामग
    -0.07
     동안
    -0.07
    _SR
    -0.06
    APER
    -0.06
     Profit
    -0.06
     regulates
    -0.06
     rozs
    -0.06
    res
    -0.06
     Helen
    -0.06
    引き
    -0.06
    POSITIVE LOGITS
    ,你
    0.07
     BSD
    0.06
     oat
    0.06
    報
    0.06
     Ae
    0.06
    gratis
    0.06
    	day
    0.06
     bought
    0.06
     int
    0.06
     queues
    0.06
    Activations Density 0.002%

    No Known Activations