© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44339
    Prev
    Next
    INDEX
    Explanations

    Academic institutions

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot verbs and nouns that describe what an institution offers or provides—e.g. “offers,” “provides,” “services,” “programs.”

    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
     triples
    -0.07
    �
    -0.07
     Brian
    -0.07
     stimulates
    -0.07
    ManyToOne
    -0.06
    /blog
    -0.06
     AOL
    -0.06
     Times
    -0.06
    WithString
    -0.06
    patients
    -0.06
    POSITIVE LOGITS
     (('
    0.07
     [\
    0.06
     vytvá
    0.06
     Hey
    0.06
     Ί
    0.06
    .imshow
    0.06
     prenatal
    0.06
     fallback
    0.06
    ='./
    0.06
     gösterir
    0.06
    Activations Density 0.097%

    No Known Activations