© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95181
    Prev
    Next
    INDEX
    Explanations

    terms related to sports seasons and game 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
    ook
    -0.07
    ant
    -0.07
    Çİ
    -0.06
    ente
    -0.06
    ly
    -0.06
     Prote
    -0.06
    quot
    -0.06
    oes
    -0.06
    1
    -0.06
    umen
    -0.06
    POSITIVE LOGITS
    _tF
    0.07
    _tD
    0.07
    ázev
    0.07
    -UA
    0.07
    _tE
    0.07
    eworld
    0.07
    _mE
    0.07
    psc
    0.06
    mans
    0.06
    XM
    0.06
    Activations Density 0.008%

    No Known Activations