© 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. 15-LLAMASCOPE-RES-131K
    11. 61680
    Prev
    Next
    INDEX
    Explanations

    terms related to industrial activities and structures

    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
    urer
    -0.08
    ãĥĨãĥ«
    -0.08
    ï¸
    -0.08
    onders
    -0.08
    holes
    -0.08
    ustin
    -0.07
    onder
    -0.07
    quared
    -0.07
    bsolute
    -0.07
    eldon
    -0.07
    POSITIVE LOGITS
    ized
    0.09
    ization
    0.08
    ised
    0.07
    anzi
    0.07
    -scale
    0.07
    izr
    0.07
    ////////////////////////////////////////////////////////////////////////////////↵↵
    0.07
    izing
    0.07
    isation
    0.06
    l
    0.06
    Activations Density 0.009%

    No Known Activations