© 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. 107475
    Prev
    Next
    INDEX
    Explanations

    terms related to sports schedules and regulations

    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
    å¼¥
    -0.08
    _FOREACH
    -0.08
    vrd
    -0.07
    Invariant
    -0.07
     intermediate
    -0.07
    apses
    -0.07
     intermedi
    -0.06
    .isFile
    -0.06
    ÅĤÄħ
    -0.06
    ãģıãģł
    -0.06
    POSITIVE LOGITS
     conflict
    0.13
     conflicts
    0.12
     interference
    0.12
     clash
    0.11
     competition
    0.10
     Conflict
    0.10
    Conflict
    0.10
     overlaps
    0.09
     conflicting
    0.09
     interfere
    0.09
    Activations Density 0.108%

    No Known Activations