© 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. 109773
    Prev
    Next
    INDEX
    Explanations

    patents

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on the standalone indefinite article “a.”

    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
    ,start
    -0.07
    _normals
    -0.06
     navCtrl
    -0.06
    ILER
    -0.06
     minion
    -0.06
     ailments
    -0.06
    _fre
    -0.06
    ladesh
    -0.06
     Coinbase
    -0.06
    POSITIVE LOGITS
    íž
    0.07
    шев
    0.06
    lias
    0.06
     Europa
    0.06
     fundra
    0.06
    áš
    0.06
     acompanh
    0.06
     Čech
    0.06
    _SCORE
    0.06
    -shift
    0.06
    Activations Density 0.083%

    No Known Activations