© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16124
    Prev
    Next
    INDEX
    Explanations

    references to database operations and client libraries

    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
    ÑĥÑĩаÑģ
    -0.07
    Ñī
    -0.06
     SQLITE
    -0.06
    ÑĤаб
    -0.06
    .self
    -0.06
    profil
    -0.06
    æł¹æľ¬
    -0.06
    enties
    -0.06
    ungan
    -0.06
    rupa
    -0.06
    POSITIVE LOGITS
    iji
    0.07
    eless
    0.07
    herits
    0.06
     Zucker
    0.06
    PLICIT
    0.06
     pulumi
    0.06
    ear
    0.06
    Demon
    0.06
    UDIO
    0.06
    anko
    0.06
    Activations Density 0.022%

    No Known Activations