© 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. 41549
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the word “WARRANTIES” (as found in software license disclaimer headers).

    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
    /tree
    -0.06
     Jehovah
    -0.06
    ithe
    -0.06
    FilterWhere
    -0.06
    ,file
    -0.06
    สะ
    -0.06
    emplace
    -0.06
     americ
    -0.06
     ejemplo
    -0.06
    725
    -0.06
    POSITIVE LOGITS
     existential
    0.06
     suspect
    0.06
     비교
    0.06
     nodeList
    0.06
     필
    0.06
    Upon
    0.06
     reiterated
    0.06
    .DE
    0.06
    uid
    0.06
     taxonomy
    0.06
    Activations Density 0.000%

    No Known Activations