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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56104
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations

    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
    ished
    -0.07
    avax
    -0.07
     ÑģÑĤоÑĢ
    -0.07
    storybook
    -0.06
    :CGRect
    -0.06
     ancest
    -0.06
    emed
    -0.06
     dny
    -0.06
     Tup
    -0.06
    chia
    -0.06
    POSITIVE LOGITS
     downtown
    0.07
    -normal
    0.06
     town
    0.06
     Downtown
    0.06
    LEAN
    0.06
    weg
    0.06
    halb
    0.06
    à¸ĵะ
    0.06
    /down
    0.06
    wards
    0.06
    Activations Density 0.008%

    No Known Activations