© 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. 20156
    Prev
    Next
    INDEX
    Explanations

    matrix/array dimensions (programming)

    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
    =C
    -0.07
     distributors
    -0.07
     UF
    -0.07
    grown
    -0.06
     impatient
    -0.06
     Taliban
    -0.06
    альне
    -0.06
     folding
    -0.06
     нали
    -0.06
     Blackjack
    -0.06
    POSITIVE LOGITS
     sür
    0.07
    ümüş
    0.07
    	esc
    0.06
     errorMsg
    0.06
    $config
    0.06
     Aw
    0.06
     dagen
    0.06
     허
    0.06
    Cake
    0.06
    alış
    0.06
    Activations Density 0.022%

    No Known Activations