© 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. 83040
    Prev
    Next
    INDEX
    Explanations

    anatomical and positional terms related to body structure

    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
    ourg
    -0.08
    ols
    -0.07
    ten
    -0.07
    arez
    -0.07
    atura
    -0.07
    ulator
    -0.07
    agan
    -0.07
    elier
    -0.07
    ych
    -0.06
    nel
    -0.06
    POSITIVE LOGITS
    ward
    0.10
    -most
    0.09
    wards
    0.08
    most
    0.08
    WARDS
    0.08
     portion
    0.08
    -facing
    0.08
    /front
    0.07
    WARD
    0.07
    /up
    0.07
    Activations Density 0.013%

    No Known Activations