© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82403
    Prev
    Next
    INDEX
    Explanations

    names or identifiers of individuals involved in community or social events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .sys
    -0.07
    ña
    -0.07
    athom
    -0.06
    memcmp
    -0.06
    ño
    -0.06
    殿
    -0.06
    linger
    -0.06
     memcmp
    -0.06
     virtual
    -0.06
    885
    -0.06
    POSITIVE LOGITS
    .getAction
    0.07
    ampler
    0.06
    obil
    0.06
    ÛĮÙĨ
    0.06
    ä¼
    0.06
    åīĽ
    0.06
    εÏħ
    0.06
    ợ
    0.06
    iPad
    0.06
    IPPING
    0.05
    Activations Density 0.015%

    No Known Activations