© 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. 15-LLAMASCOPE-RES-131K
    11. 61348
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration and organization

    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
     meanwhile
    -0.07
     then
    -0.07
     however
    -0.06
    ammen
    -0.06
    /or
    -0.06
    oret
    -0.06
    iet
    -0.06
     may
    -0.05
     progress
    -0.05
     wr
    -0.05
    POSITIVE LOGITS
    :].
    0.07
    иÑģк
    0.07
    ÅĻed
    0.07
    éĮ
    0.07
    ãĤĩ
    0.07
    dech
    0.07
     bý
    0.07
     alespoÅĪ
    0.07
     zamÄĽÅĻ
    0.07
    InParameter
    0.07
    Activations Density 0.044%

    No Known Activations