© 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. 57236
    Prev
    Next
    INDEX
    Explanations

    references to specific months and seasonal conditions

    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
    esub
    -0.08
     Rubin
    -0.07
    _FOREACH
    -0.07
    èĬ³
    -0.07
    -scroll
    -0.07
    imenti
    -0.07
    ocker
    -0.07
    iminal
    -0.07
    zM
    -0.07
    оÑĤÑĢеб
    -0.07
    POSITIVE LOGITS
    apy
    0.07
    kol
    0.06
    ouv
    0.06
    2
    0.06
    json
    0.06
    1
    0.06
    tit
    0.05
    observ
    0.05
     Hire
    0.05
    otte
    0.05
    Activations Density 0.000%

    No Known Activations