© 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. 126264
    Prev
    Next
    INDEX
    Explanations

    terminology related to mining and technology systems

    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
    idian
    -0.07
    anian
    -0.07
    uss
    -0.06
     rap
    -0.06
     via
    -0.06
    нин
    -0.06
    åĤĻ
    -0.06
    871
    -0.06
    à¸Ńà¸Ļ
    -0.06
    571
    -0.06
    POSITIVE LOGITS
    orris
    0.07
     Shall
    0.07
    ãĥ
    0.07
     shall
    0.07
    @js
    0.06
    shall
    0.06
     Ãľn
    0.06
    Unicode
    0.06
    bsub
    0.06
    entric
    0.06
    Activations Density 0.009%

    No Known Activations