© 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. 74904
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and syntax elements

    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
    ĨĴ
    -0.08
    esting
    -0.07
     tail
    -0.07
    nech
    -0.07
    esters
    -0.06
    prompt
    -0.06
    lea
    -0.06
    keley
    -0.06
    brero
    -0.06
    iguiente
    -0.06
    POSITIVE LOGITS
     early
    0.12
     childhood
    0.12
    early
    0.11
     Early
    0.10
    Early
    0.09
    æĹ©
    0.09
     Childhood
    0.09
     init
    0.08
     onLoad
    0.08
     earliest
    0.07
    Activations Density 0.005%

    No Known Activations