© 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. 68959
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the negation “not.”

    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
    literal
    -0.07
     abbiamo
    -0.07
     شعر
    -0.07
     frowned
    -0.07
     Dort
    -0.07
    Answer
    -0.07
    ONDON
    -0.07
     облад
    -0.07
    216
    -0.07
    ena
    -0.06
    POSITIVE LOGITS
    /W
    0.06
    /k
    0.06
     vlastní
    0.06
     вимог
    0.06
    �
    0.06
    \n
    0.06
    .rot
    0.06
    _pri
    0.06
     scho
    0.06
     privat
    0.06
    Activations Density 0.022%

    No Known Activations