© 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. 29916
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
    innie
    -0.06
    niej
    -0.06
     Ale
    -0.06
    опаÑģ
    -0.06
    ANTED
    -0.06
    uele
    -0.06
    chant
    -0.06
     Nel
    -0.06
    uel
    -0.06
    aoke
    -0.06
    POSITIVE LOGITS
    ://
    0.07
    abase
    0.06
    _ENC
    0.06
    quiv
    0.06
    rought
    0.06
    ạn
    0.06
    pard
    0.06
    raž
    0.06
     quarter
    0.06
    ori
    0.06
    Activations Density 0.008%

    No Known Activations