© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 31097
    Prev
    Next
    INDEX
    Explanations

    articles

    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
     viper
    -0.07
     laser
    -0.06
     lasers
    -0.06
     مق
    -0.06
    fabs
    -0.06
    .vis
    -0.06
    iselect
    -0.06
    IGENCE
    -0.06
    먼
    -0.06
    acades
    -0.06
    POSITIVE LOGITS
     overwhelmingly
    0.07
    Fixture
    0.06
    _Button
    0.06
     एक
    0.06
     evaluator
    0.06
     Ideally
    0.06
     Tmax
    0.06
     Abr
    0.06
     assert
    0.06
     그의
    0.06
    Activations Density 0.079%

    No Known Activations