© 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. 55847
    Prev
    Next
    INDEX
    Explanations

    terms related to listings and demographics

    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
    ollen
    -0.09
     Latter
    -0.07
    URN
    -0.07
    loon
    -0.06
    acket
    -0.06
    erken
    -0.06
    aches
    -0.06
    owns
    -0.06
    -ng
    -0.06
    rahim
    -0.06
    POSITIVE LOGITS
    etros
    0.07
    raphics
    0.07
    à¤łà¤¨
    0.06
    /dat
    0.06
    ì¸
    0.06
    anlı
    0.06
    porter
    0.06
    æŀ
    0.06
    eland
    0.06
    ands
    0.06
    Activations Density 0.001%

    No Known Activations