© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 128460
    Prev
    Next
    INDEX
    Explanations

    yellow

    np_max-act · gemini-2.0-flash

    The neuron fires on individual domain-specific category words—typically technical nouns naming types of things (e.g. pigment “yellow,” organ names like “lung,” “kidney,” “skin,” insurance “auto,” interface “contacts,” etc.).

    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
    message
    -0.07
     cli
    -0.06
    òa
    -0.06
     weights
    -0.06
    ーリ
    -0.06
     fie
    -0.06
    847
    -0.06
    heels
    -0.06
    .cross
    -0.06
    (reordered
    -0.06
    POSITIVE LOGITS
     इक
    0.07
     damned
    0.07
     Alternative
    0.07
     IEnumerator
    0.07
     Editing
    0.06
    AUT
    0.06
     COMPLETE
    0.06
    Tutorial
    0.06
     AVAILABLE
    0.06
    ACTION
    0.06
    Activations Density 0.314%

    No Known Activations