© 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. 78840
    Prev
    Next
    INDEX
    Explanations

    terms related to holidays and festive 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
    olini
    -0.07
    once
    -0.06
     Pron
    -0.06
     Turns
    -0.06
     san
    -0.05
    ular
    -0.05
    ius
    -0.05
    ÑģÑĤво
    -0.05
     attachment
    -0.05
    ilden
    -0.05
    POSITIVE LOGITS
    -themed
    0.11
    $MESS
    0.09
    ayah
    0.09
    keh
    0.08
     themed
    0.08
    -theme
    0.08
     theme
    0.08
    аÑĤегоÑĢ
    0.08
    oriented
    0.07
    REEN
    0.07
    Activations Density 0.013%

    No Known Activations