© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94010
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and associated travel details

    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
    Wunused
    -0.07
    enko
    -0.07
    opard
    -0.07
    #Region
    -0.06
    arend
    -0.06
     appart
    -0.06
     (~(
    -0.06
    ">ÃĹ</
    -0.06
    nodeName
    -0.06
     Bans
    -0.06
    POSITIVE LOGITS
     Weiner
    0.06
     pred
    0.06
    /goto
    0.06
     Conrad
    0.06
    ossier
    0.06
    ÙĪØ·
    0.06
     Eph
    0.06
     repr
    0.06
    hed
    0.06
    onyms
    0.06
    Activations Density 0.005%

    No Known Activations