© 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. 55849
    Prev
    Next
    INDEX
    Explanations

    provided

    np_max-act · gemini-2.0-flash

    This neuron detects software license warranty disclaimer statements (phrases like “provided … as-is, without any express or implied warranty”).

    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
    Ố
    -0.08
    ック
    -0.07
    ibility
    -0.06
    Stock
    -0.06
    Manip
    -0.06
    يس
    -0.06
     barric
    -0.06
     Lex
    -0.06
    tems
    -0.06
    εύ
    -0.06
    POSITIVE LOGITS
     fragment
    0.07
     pulses
    0.06
     образования
    0.06
     mediaPlayer
    0.06
    Sequential
    0.06
     "'",
    0.06
     také
    0.06
     QObject
    0.06
     reloc
    0.06
     surrender
    0.06
    Activations Density 0.002%

    No Known Activations