© 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. 126825
    Prev
    Next
    INDEX
    Explanations

    summaries

    np_max-act · gemini-2.0-flash

    This neuron fires on evaluative sentiment words—adjectives or adverbs expressing positive or negative opinion.

    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
    sth
    -0.06
    descending
    -0.06
    mony
    -0.06
     tong
    -0.06
    zburg
    -0.06
    urses
    -0.06
     Knife
    -0.06
    France
    -0.05
    atz
    -0.05
     vil
    -0.05
    POSITIVE LOGITS
    화
    0.07
    formedURLException
    0.07
     tienen
    0.07
    Cre
    0.06
    _CHANGE
    0.06
     UITextView
    0.06
     indign
    0.06
    _sf
    0.06
    áci
    0.06
    _sha
    0.06
    Activations Density 0.076%

    No Known Activations