© 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. 129838
    Prev
    Next
    INDEX
    Explanations

    forum posts/comments

    np_max-act · gemini-2.0-flash

    The neuron detects words that express negation of authenticity or falsity (e.g. “not,” “real,” “fake”).

    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
    ks
    -0.07
     Px
    -0.06
     payment
    -0.06
    ра�
    -0.06
     Goldman
    -0.06
    �
    -0.06
    _resize
    -0.06
    熟
    -0.06
     belonging
    -0.06
    erspective
    -0.06
    POSITIVE LOGITS
    _STMT
    0.08
     `.
    0.07
    (car
    0.07
     TY
    0.07
    __.'/
    0.06
    _SCR
    0.06
    vrolet
    0.06
     Hers
    0.06
    updating
    0.06
    riot
    0.06
    Activations Density 0.082%

    No Known Activations