© 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. 11-RESID-POST-AA
    6. 44205
    Prev
    Next
    INDEX
    Explanations

    lines

    np_max-act · gemini-2.0-flash

    The neuron activates whenever the text mentions “lines,” i.e. when the user refers to lines (typically in a request like “write some lines” or “give me X lines”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мяс
    -0.07
    咨
    -0.07
    lando
    -0.06
    .places
    -0.06
     ortaya
    -0.06
    아서
    -0.06
     bevor
    -0.06
     shl
    -0.06
     typeName
    -0.06
     поск
    -0.06
    POSITIVE LOGITS
     lines
    0.11
     line
    0.09
    horizontal
    0.08
     Lines
    0.07
     Line
    0.07
    -lines
    0.07
     authorised
    0.07
    (ident
    0.07
    StrLn
    0.07
     strip
    0.06
    Activations Density 0.018%

    No Known Activations