© 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. 117567
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their actions or roles in contexts involving teamwork and performance

    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
    ICON
    -0.08
    ocache
    -0.08
    chg
    -0.07
    parator
    -0.07
    vsp
    -0.07
    elib
    -0.07
    anian
    -0.07
    unny
    -0.07
    clud
    -0.06
    ån
    -0.06
    POSITIVE LOGITS
     theirs
    0.07
     ours
    0.07
     Fortune
    0.07
     did
    0.06
     hers
    0.06
     Farrell
    0.06
     accordingly
    0.06
     mine
    0.06
     Rab
    0.06
    zel
    0.06
    Activations Density 0.036%

    No Known Activations