© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73903
    Prev
    Next
    INDEX
    Explanations

    Hyphenated words

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on sub‐tokens and word fragments that occur in hyphenated compound terms (e.g. the parts of “left-turning,” “weather-risk,” “long-term,” 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
     Jihad
    -0.06
     icy
    -0.06
     비밀글
    -0.06
     reflexivity
    -0.06
    вав
    -0.06
     ntohs
    -0.06
     unlock
    -0.06
    �
    -0.06
    .setOnItemClickListener
    -0.06
     ढ
    -0.05
    POSITIVE LOGITS
    -A
    0.12
    -N
    0.11
    -up
    0.11
    -Ch
    0.10
    -Up
    0.10
    -P
    0.10
    -R
    0.10
    -Z
    0.10
    -Out
    0.10
    -J
    0.10
    Activations Density 0.855%

    No Known Activations