Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43630
    Prev
    Next
    INDEX
    Explanations

    geographical locations or place names in a specific 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
    éis
    -0.07
    IIIK
    -0.06
    ystick
    -0.06
    yx
    -0.06
     allen
    -0.06
    3
    -0.06
     manic
    -0.06
    askell
    -0.06
    forme
    -0.06
    9
    -0.06
    POSITIVE LOGITS
    pur
    0.14
    apur
    0.13
    argar
    0.12
    ipur
    0.12
    para
    0.10
     village
    0.10
    igram
    0.10
    gram
    0.10
    ihat
    0.10
    oli
    0.10
    Activations Density 0.014%

    No Known Activations