© 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 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. 17-LLAMASCOPE-RES-131K
    11. 126652
    Prev
    Next
    INDEX
    Explanations

    words related to academic programs and eligibility criteria

    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
    ิหาร
    -0.07
    ãĥ¼ãĥģ
    -0.06
    izard
    -0.06
    igit
    -0.06
    acher
    -0.06
    ieri
    -0.06
    adium
    -0.06
    heure
    -0.06
    cms
    -0.06
    ाश
    -0.06
    POSITIVE LOGITS
     minimum
    0.07
    à¥ĩण
    0.07
    ][_
    0.07
    'gc
    0.06
     baÅŁÄ±na
    0.06
     Minimum
    0.06
     OR
    0.06
     alespoÅĪ
    0.06
    chet
    0.06
    XXXX
    0.06
    Activations Density 0.008%

    No Known Activations