© 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. 5-LLAMASCOPE-RES-131K
    11. 125987
    Prev
    Next
    INDEX
    Explanations

    programming constructs and terms related to data loading or processing

    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
    icari
    -0.07
    enate
    -0.07
    spender
    -0.07
    imler
    -0.07
    ublisher
    -0.07
    gili
    -0.07
    ainless
    -0.07
    acias
    -0.07
    Ø·
    -0.06
    ież
    -0.06
    POSITIVE LOGITS
    Via
    0.06
    leigh
    0.06
    iy
    0.06
     Rentals
    0.06
     colour
    0.06
    gest
    0.06
    yy
    0.06
    est
    0.05
    t
    0.05
    Svc
    0.05
    Activations Density 0.001%

    No Known Activations