© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12962
    Prev
    Next
    INDEX
    Explanations

    Microsoft

    np_max-act · gemini-2.0-flash

    keywords related to recovery and troubleshooting of software issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags filesystem path components (e.g. directory names and separators) in answers.

    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
    leveland
    -0.07
     Cleveland
    -0.06
     Králové
    -0.06
    mediately
    -0.06
     ander
    -0.06
    terminate
    -0.06
     tkinter
    -0.06
     đô
    -0.06
     wisely
    -0.06
    enerated
    -0.06
    POSITIVE LOGITS
    .deg
    0.07
     distributor
    0.06
    ateral
    0.06
    _Details
    0.06
     Với
    0.06
    _coin
    0.06
    fails
    0.06
     redistrib
    0.06
    .labelX
    0.06
    losing
    0.06
    Activations Density 0.013%

    No Known Activations