© 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. 91740
    Prev
    Next
    INDEX
    Explanations

    International relations/conflict warnings

    np_max-act · gemini-2.0-flash

    The neuron is looking for markers of reported speech or quotations—including colons, attribution verbs (like “said”), and the surrounding framing language.

    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
     Liability
    -0.06
     詳細
    -0.06
     insanın
    -0.06
    YPD
    -0.06
    _Cmd
    -0.06
    igion
    -0.06
     ngành
    -0.06
    _indent
    -0.06
     apopt
    -0.06
    �로
    -0.05
    POSITIVE LOGITS
     phot
    0.08
     sä
    0.07
    }()↵↵
    0.07
     sam
    0.06
     kommun
    0.06
    /flutter
    0.06
    },'
    0.06
    (@
    0.06
    ----------↵↵
    0.06
     Ils
    0.06
    Activations Density 0.029%

    No Known Activations