© 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. 75209
    Prev
    Next
    INDEX
    Explanations

    elements and properties of geometric shapes in a mathematical context

    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
    comma
    -0.07
    anke
    -0.07
    ourse
    -0.07
    estre
    -0.07
    icolon
    -0.07
    -thumbnails
    -0.06
    ãĥ³ãĥ
    -0.06
    Ellipse
    -0.06
    rectangle
    -0.06
    dom
    -0.06
    POSITIVE LOGITS
    çĤİ
    0.07
    icina
    0.06
    utherland
    0.06
    ASA
    0.06
    üç
    0.06
     Figure
    0.06
     volatile
    0.06
     showc
    0.06
    .faces
    0.06
    egie
    0.06
    Activations Density 0.017%

    No Known Activations