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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 83700
    Prev
    Next
    INDEX
    Explanations

    died

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lerden
    -0.07
     Xml
    -0.07
     >=
    -0.06
    mé
    -0.06
    .uk
    -0.06
    aley
    -0.06
     Fou
    -0.06
     advisers
    -0.06
    Jamie
    -0.06
    .term
    -0.06
    POSITIVE LOGITS
     componentDidMount
    0.07
    时代
    0.06
     به
    0.06
     domest
    0.06
     ülke
    0.06
     můž
    0.06
    {:
    0.06
    说话
    0.06
    @pytest
    0.06
     bootstrap
    0.06
    Activations Density 0.015%

    No Known Activations