© 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. 82722
    Prev
    Next
    INDEX
    Explanations

    names of locations and associated context

    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
    edir
    -0.06
    LING
    -0.06
    eday
    -0.06
     Disc
    -0.06
    sep
    -0.05
     Stocks
    -0.05
    uju
    -0.05
     ry
    -0.05
    ucs
    -0.05
    ô
    -0.05
    POSITIVE LOGITS
    ÑĪев
    0.07
    να
    0.06
    tica
    0.06
     ApplicationException
    0.06
    /Area
    0.06
    رÙģ
    0.06
     Phong
    0.06
    culate
    0.06
    ji
    0.06
    ãĥķãĤ
    0.06
    Activations Density 0.008%

    No Known Activations