© 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. 28113
    Prev
    Next
    INDEX
    Explanations

    expressions of collective intent or desire

    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
    oen
    -0.07
    rea
    -0.07
    á»įt
    -0.06
    ulos
    -0.06
    /fa
    -0.06
     metres
    -0.06
    inde
    -0.06
    ollect
    -0.06
    amu
    -0.06
    PIP
    -0.06
    POSITIVE LOGITS
     aim
    0.09
     aims
    0.08
     wanted
    0.08
     hopes
    0.07
     therefore
    0.07
     attempt
    0.07
     chance
    0.07
     want
    0.07
    )const
    0.07
     attempts
    0.07
    Activations Density 0.038%

    No Known Activations