© 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. 94176
    Prev
    Next
    INDEX
    Explanations

    references to planning or arrangements for activities or events

    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
    nock
    -0.07
    eth
    -0.07
    ilis
    -0.06
    NOW
    -0.06
    imension
    -0.06
    lags
    -0.06
    nic
    -0.06
    vid
    -0.06
     ÑģооÑĤвеÑĤ
    -0.06
    agas
    -0.06
    POSITIVE LOGITS
    mant
    0.07
     eventual
    0.07
    erus
    0.07
    Reuse
    0.07
     Fancy
    0.07
     later
    0.07
    ìĥģ
    0.07
    584
    0.06
    ancers
    0.06
    Ñĸг
    0.06
    Activations Density 0.015%

    No Known Activations