© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27306
    Prev
    Next
    INDEX
    Explanations

    references to membership policies and requirements

    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
    undi
    -0.07
    phia
    -0.07
     ç©
    -0.06
    ضا
    -0.06
     Learned
    -0.06
    eshire
    -0.06
    IndexChanged
    -0.06
    icens
    -0.06
    oney
    -0.06
    .jetbrains
    -0.06
    POSITIVE LOGITS
    CastException
    0.07
    ÏĨεÏģ
    0.07
    ADATA
    0.07
    åīĩ
    0.07
     guest
    0.06
    auer
    0.06
     atIndex
    0.06
    .Assertions
    0.06
    .generated
    0.06
    UMP
    0.06
    Activations Density 0.016%

    No Known Activations