© 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. 83966
    Prev
    Next
    INDEX
    Explanations

    numerical data and results related to games and scores

    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
    allet
    -0.07
    inalg
    -0.07
    unei
    -0.06
    -turned
    -0.06
    ahren
    -0.06
    amedi
    -0.06
    боÑĢ
    -0.06
    IEW
    -0.06
    urret
    -0.06
    uania
    -0.05
    POSITIVE LOGITS
     double
    0.09
     DOUBLE
    0.09
     two
    0.09
     Double
    0.09
    DoubleClick
    0.08
    double
    0.08
     Two
    0.08
     doubly
    0.08
    åıĮ
    0.08
    Double
    0.08
    Activations Density 0.025%

    No Known Activations