© 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. 118380
    Prev
    Next
    INDEX
    Explanations

    terms related to logical reasoning and structured thought

    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
    ifr
    -0.08
    akan
    -0.07
    hangi
    -0.07
    reh
    -0.07
    een
    -0.07
    erman
    -0.07
    illance
    -0.07
    ervas
    -0.07
    holm
    -0.07
    isman
    -0.07
    POSITIVE LOGITS
    /log
    0.09
    /math
    0.09
    istically
    0.09
    istic
    0.08
    ically
    0.08
    inalg
    0.07
    ton
    0.07
    ALLY
    0.07
    istical
    0.07
    -minded
    0.07
    Activations Density 0.006%

    No Known Activations