© 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. 93677
    Prev
    Next
    INDEX
    Explanations

    references to minutes, reports, and records from meetings or proceedings

    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
     Champ
    -0.07
    _triggered
    -0.07
    زار
    -0.07
    ç¹
    -0.06
    ej
    -0.06
     Postal
    -0.06
    _mapped
    -0.06
    евиÑĩ
    -0.06
    rå
    -0.06
    grave
    -0.06
    POSITIVE LOGITS
    obl
    0.08
     record
    0.07
    marshall
    0.07
    .Experimental
    0.07
    ÄĻ
    0.07
    ÏĥμαÏĦα
    0.07
    verbatim
    0.06
    aneous
    0.06
    ebek
    0.06
     Leigh
    0.06
    Activations Density 0.003%

    No Known Activations