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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 3-RESID-POST-AA
    6. 122100
    Prev
    Next
    INDEX
    Explanations

    var

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     einf
    -0.06
     díky
    -0.06
    hdl
    -0.06
     convinc
    -0.06
    �
    -0.06
    óng
    -0.06
     graz
    -0.06
    PWM
    -0.06
     ड
    -0.06
    368
    -0.06
    POSITIVE LOGITS
    	var
    0.15
     var
    0.10
    var
    0.08
    .workspace
    0.08
    _QUESTION
    0.07
    isted
    0.06
    .btnAdd
    0.06
     unborn
    0.06
    _CHARACTER
    0.06
     Tiny
    0.06
    Activations Density 0.002%

    No Known Activations