© 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. 75398
    Prev
    Next
    INDEX
    Explanations

    elements of mathematical proofs and logical reasoning

    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
    ioni
    -0.08
     bì
    -0.07
    енÑĮ
    -0.07
    <<<
    -0.07
     promot
    -0.07
    аÑĢам
    -0.06
    Ctrls
    -0.06
     Snyder
    -0.06
     scrim
    -0.06
     Cue
    -0.06
    POSITIVE LOGITS
     automatically
    0.07
     indirectly
    0.07
     immediately
    0.07
     Ded
    0.07
     via
    0.07
     consequences
    0.07
     Rud
    0.07
    ipo
    0.06
     automatic
    0.06
     Immediately
    0.06
    Activations Density 0.119%

    No Known Activations