© 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. 15-RESID-POST-AA
    6. 68869
    Prev
    Next
    INDEX
    Explanations

    another

    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
    _ROLE
    -0.07
    'on
    -0.06
     司
    -0.06
    entialAction
    -0.06
    _fact
    -0.06
    ertime
    -0.06
    /documents
    -0.06
    get
    -0.06
    っと
    -0.06
    ing
    -0.06
    POSITIVE LOGITS
     Watts
    0.08
    ########
    0.07
       
    0.06
     magma
    0.06
     Затем
    0.06
     onemocnění
    0.06
     |-
    0.06
     dynamic
    0.06
    ilo
    0.06
    _EXPRESSION
    0.06
    Activations Density 0.000%

    No Known Activations