© 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. 6897
    Prev
    Next
    INDEX
    Explanations

    told

    np_max-act · gemini-2.0-flash

    This neuron detects reporting or attribution verbs (e.g. "told," "said," "asked") that introduce quoted or reported speech.

    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
    -alpha
    -0.07
    ++]
    -0.06
    .authService
    -0.06
     buckle
    -0.06
    SplitOptions
    -0.06
     compression
    -0.06
     diligent
    -0.06
    imitive
    -0.06
    [Double
    -0.06
    .Does
    -0.06
    POSITIVE LOGITS
    JA
    0.08
    _Re
    0.07
    oke
    0.07
     μου
    0.06
     dern
    0.06
    _Res
    0.06
    lsx
    0.06
     сразу
    0.06
    ỡ
    0.06
     told
    0.06
    Activations Density 0.023%

    No Known Activations