© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55383
    Prev
    Next
    INDEX
    Explanations

    predicted

    np_max-act · gemini-2.0-flash

    The neuron spotlights technical qualifier terms in molecular‐biology methods sections—especially words like “predicted,” “putative,” “open/read­ing frame,” “deduced,” and the numeric values that follow them.

    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
     cloudy
    -0.08
    �
    -0.07
     directed
    -0.06
    xdd
    -0.06
    ModelProperty
    -0.06
    eed
    -0.06
     Lace
    -0.06
     repetitions
    -0.06
    вий
    -0.06
     formulated
    -0.06
    POSITIVE LOGITS
    웨어
    0.07
     Forum
    0.07
     tmpl
    0.06
     розвитку
    0.06
     cdecl
    0.06
    	panic
    0.06
    ใจ
    0.06
     genie
    0.06
     doInBackground
    0.06
     verze
    0.06
    Activations Density 0.005%

    No Known Activations