© 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. 91705
    Prev
    Next
    INDEX
    Explanations

    matrix

    np_max-act · gemini-2.0-flash

    The neuron fires on technical references to “active matrix” display devices and their driving or signal-line driver circuitry.

    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
     tolerance
    -0.07
     proceed
    -0.06
    astr
    -0.06
    -report
    -0.06
    .urlopen
    -0.06
     Uploaded
    -0.06
     genital
    -0.06
    _above
    -0.06
    itunes
    -0.06
     compound
    -0.06
    POSITIVE LOGITS
    ,-
    0.07
    jac
    0.06
     Matlab
    0.06
     anyone
    0.06
    เซอร
    0.06
    مز
    0.06
     druhé
    0.06
    _PENDING
    0.06
     Allows
    0.06
    naissance
    0.06
    Activations Density 0.001%

    No Known Activations