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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15503
    Prev
    Next
    INDEX
    Explanations

    themes of conflict and struggle, particularly between different groups

    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
    ãĥ¼ãĥ³
    -0.06
    ornado
    -0.06
    weeney
    -0.06
    enate
    -0.06
    prend
    -0.06
    edula
    -0.06
    yne
    -0.05
    OLTIP
    -0.05
    oner
    -0.05
    igli
    -0.05
    POSITIVE LOGITS
    MUX
    0.07
    Animating
    0.07
     Dome
    0.07
    ýval
    0.07
     Hammond
    0.07
     {?>↵
    0.07
    arel
    0.07
    ÄĻp
    0.07
    aniu
    0.07
     clearfix
    0.06
    Activations Density 0.006%

    No Known Activations