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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126731
    Prev
    Next
    INDEX
    Explanations

    elements related to collaborative efforts and teamwork

    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
    ilan
    -0.07
    raith
    -0.07
    -copy
    -0.07
    intree
    -0.07
    hiba
    -0.07
    yth
    -0.06
    onnement
    -0.06
    abar
    -0.06
    igua
    -0.06
    İ
    -0.06
    POSITIVE LOGITS
     when
    0.07
    à¸Ĥà¸ĵะà¸Ĺ
    0.06
     unde
    0.06
    975
    0.06
    :description
    0.06
     analogue
    0.06
    pons
    0.06
     while
    0.06
    bjerg
    0.06
     Rot
    0.05
    Activations Density 0.033%

    No Known Activations