© 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. 11-RESID-POST-AA
    6. 75045
    Prev
    Next
    INDEX
    Explanations

    non-English languages and code

    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
    _bag
    -0.07
    both
    -0.07
    orang
    -0.07
     deportation
    -0.06
    [node
    -0.06
     Ayrıca
    -0.06
    _difference
    -0.06
    .longitude
    -0.06
     alumnos
    -0.06
    كس
    -0.06
    POSITIVE LOGITS
     base
    0.07
     dev
    0.07
     based
    0.07
     مو
    0.06
     grated
    0.06
    '''
    ↵
    0.06
     (*)
    0.06
     assumption
    0.06
    _BASE
    0.06
     b
    0.06
    Activations Density 0.020%

    No Known Activations