© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3033
    Prev
    Next
    INDEX
    Explanations

    mentions of significant highlights or standout moments

    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
    anson
    -0.07
    ubat
    -0.07
    алеж
    -0.07
    -sided
    -0.06
    à¤
    -0.06
    amon
    -0.06
    TokenType
    -0.06
    idth
    -0.06
    aly
    -0.06
    linger
    -0.06
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.09
    人çī©
    0.07
     reel
    0.07
    æĭĶ
    0.07
    576
    0.07
    yat
    0.06
    ara
    0.06
     rencont
    0.06
    USTER
    0.06
    QRS
    0.06
    Activations Density 0.006%

    No Known Activations