© 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. 126797
    Prev
    Next
    INDEX
    Explanations

    references to academic discussions and collaborations within a scientific context

    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
     ÎľÎŃ
    -0.07
     Ùģار
    -0.06
    oday
    -0.06
     omas
    -0.06
    kin
    -0.06
    599
    -0.06
    ofire
    -0.06
     Tie
    -0.06
    okin
    -0.06
    resent
    -0.06
    POSITIVE LOGITS
     DNA
    0.08
    aria
    0.07
    marks
    0.07
    ookie
    0.07
    ewire
    0.07
    usto
    0.06
     Wr
    0.06
     methyl
    0.06
    .NewReader
    0.06
    alte
    0.06
    Activations Density 0.020%

    No Known Activations