© 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. 92550
    Prev
    Next
    INDEX
    Explanations

    pository

    np_max-act · gemini-2.0-flash

    This neuron detects instructions for adding or specifying software repositories (e.g. “add-apt-repository”/“ppa”) in Ubuntu installation commands.

    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
    }↵↵
    -0.07
    RuntimeObject
    -0.07
     CAM
    -0.07
    _MAT
    -0.06
    WithIdentifier
    -0.06
    dry
    -0.06
    ć
    -0.06
    ?>↵↵↵
    -0.06
     m
    -0.06
     ";↵↵
    -0.06
    POSITIVE LOGITS
     lucky
    0.06
    ního
    0.06
    ITUDE
    0.06
    .DateTime
    0.06
     disadvantaged
    0.06
    :no
    0.06
    (repo
    0.06
    .graphics
    0.06
    ンス
    0.06
    erness
    0.06
    Activations Density 0.000%

    No Known Activations