© 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. 3970
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or entities

    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
    мм
    -0.07
    trys
    -0.07
    angel
    -0.07
    ä»°
    -0.06
    ücken
    -0.06
    esi
    -0.06
    chten
    -0.06
    OWL
    -0.06
    nan
    -0.06
    outh
    -0.06
    POSITIVE LOGITS
    稿
    0.07
    ardin
    0.07
    lessly
    0.07
    rase
    0.06
    ebe
    0.06
    icie
    0.06
    udden
    0.06
     Sabha
    0.06
    awi
    0.06
    gin
    0.06
    Activations Density 0.010%

    No Known Activations