© 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. 70960
    Prev
    Next
    INDEX
    Explanations

    references to time and temporal progression

    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
    lech
    -0.08
    PÅĻi
    -0.07
    AZE
    -0.07
    ahan
    -0.07
    anje
    -0.07
    ãĥ¼ãĥ³
    -0.07
    ruz
    -0.07
    erece
    -0.07
    eness
    -0.07
    ISHED
    -0.06
    POSITIVE LOGITS
    sto
    0.08
    ë§Īëĭ¤
    0.07
    -wise
    0.07
    stown
    0.07
    lessly
    0.06
    imals
    0.06
    ами
    0.06
     Hatch
    0.06
     wise
    0.06
    ommen
    0.06
    Activations Density 0.008%

    No Known Activations