© 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. 76312
    Prev
    Next
    INDEX
    Explanations

    inquiries related to the reasons behind various phenomena

    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
    olor
    -0.07
    oler
    -0.07
    ay
    -0.06
    olet
    -0.06
    grp
    -0.06
    ãģĵãģ¨
    -0.06
    ÚĨÛĮ
    -0.06
    lesai
    -0.06
    ýš
    -0.06
    ukes
    -0.06
    POSITIVE LOGITS
     borderBottom
    0.07
    aea
    0.06
    unga
    0.06
    称
    0.06
    одав
    0.06
    çª
    0.06
    displayName
    0.06
    utter
    0.06
    prü
    0.06
    redential
    0.06
    Activations Density 0.003%

    No Known Activations