© 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. 57171
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic writing

    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
    usat
    -0.07
    æľ¬
    -0.06
    424
    -0.06
    683
    -0.06
    ød
    -0.06
    åī¯
    -0.06
    ãĥĥ
    -0.06
    412
    -0.06
    borg
    -0.06
    ìĬµ
    -0.06
    POSITIVE LOGITS
    #ac
    0.07
    fcn
    0.07
    ounty
    0.06
    imports
    0.06
    .DropTable
    0.06
    (cos
    0.06
    åīĽ
    0.06
     Klopp
    0.06
    üf
    0.06
     Bout
    0.06
    Activations Density 0.011%

    No Known Activations