© 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. 87247
    Prev
    Next
    INDEX
    Explanations

    the presence of LaTeX formatting or code

    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
    activex
    -0.09
    rlen
    -0.09
    nict
    -0.08
    ÑĢеж
    -0.08
    еÑĢк
    -0.08
    senal
    -0.08
    оÑģлав
    -0.08
    cription
    -0.08
    (æĹ¥
    -0.08
    hti
    -0.08
    POSITIVE LOGITS
     vice
    0.06
     non
    0.06
     ad
    0.05
    shape
    0.05
    erg
    0.05
     Caval
    0.05
    ph
    0.05
     minus
    0.05
    oj
    0.05
     se
    0.05
    Activations Density 0.028%

    No Known Activations