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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-LLAMASCOPE-RES-131K
    6. 96048
    Prev
    Next
    INDEX
    Explanations

    suffixes or prefixes that suggest geographic or location-based terms

    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
    à¸ģร
    -0.07
    sey
    -0.06
    neys
    -0.06
    ktor
    -0.06
    rez
    -0.06
    upal
    -0.06
     kind
    -0.06
    ucking
    -0.06
    mpr
    -0.06
     meaning
    -0.06
    POSITIVE LOGITS
    venue
    0.07
     бой
    0.07
    .setInput
    0.07
    oden
    0.06
     domest
    0.06
     Barnett
    0.06
     بÙĪ
    0.06
    Æ¡
    0.06
    è¨
    0.06
    uzu
    0.06
    Activations Density 0.008%

    No Known Activations