© 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. 74853
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structure in formal proofs

    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
    çĨ
    -0.06
    ington
    -0.06
    INGTON
    -0.05
     subur
    -0.05
    ажд
    -0.05
     hala
    -0.05
    اتر
    -0.05
     Hurricane
    -0.05
    rung
    -0.05
    nth
    -0.05
    POSITIVE LOGITS
    .UnitTesting
    0.10
    aseline
    0.07
    eldorf
    0.07
    .spy
    0.07
    ÏĢει
    0.07
    jec
    0.07
    iddi
    0.07
    asure
    0.07
    è§ī
    0.07
    TRGL
    0.07
    Activations Density 0.097%

    No Known Activations