© 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. 94748
    Prev
    Next
    INDEX
    Explanations

    recognition of student achievements and contributions to the school community

    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
    alias
    -0.07
    .tc
    -0.07
    affe
    -0.06
    ulen
    -0.06
    actal
    -0.06
     existence
    -0.06
    ']!='
    -0.06
    Thr
    -0.06
    thr
    -0.06
    entar
    -0.06
    POSITIVE LOGITS
     evid
    0.07
    ãģ°ãģĭãĤĬ
    0.06
    utsch
    0.06
     Ownership
    0.06
     =&
    0.06
     quiet
    0.06
    HW
    0.06
    .Assign
    0.06
     Trouble
    0.06
     progress
    0.06
    Activations Density 0.022%

    No Known Activations