© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82588
    Prev
    Next
    INDEX
    Explanations

    mentions of newsletters or newsletter sign-up opportunities

    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
     Kling
    -0.07
    emer
    -0.06
    entin
    -0.06
    à¸ij
    -0.06
    stk
    -0.06
    exion
    -0.06
     suck
    -0.06
    essel
    -0.06
    leur
    -0.06
     Franken
    -0.06
    POSITIVE LOGITS
    ipc
    0.07
    à¸Ńà¸ļ
    0.07
    iri
    0.06
     pev
    0.06
     æ·
    0.06
    avn
    0.06
    åļ
    0.06
    /support
    0.06
    MSN
    0.06
     rencont
    0.06
    Activations Density 0.002%

    No Known Activations