© 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. 73644
    Prev
    Next
    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting reporting‐style attribution verbs (e.g. “says,” “said,” “reports”) that signal 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
     THE
    -0.07
    地球
    -0.07
    อท
    -0.07
     magnesium
    -0.06
    电话
    -0.06
    即
    -0.06
     so
    -0.06
    ерь
    -0.06
    234
    -0.06
    (login
    -0.06
    POSITIVE LOGITS
    records
    0.07
    ъек
    0.07
    	size
    0.06
    frog
    0.06
    ousel
    0.06
    غم
    0.06
    excerpt
    0.06
    _hor
    0.06
    :none
    0.06
    /install
    0.06
    Activations Density 0.146%

    No Known Activations