© 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. 5-LLAMASCOPE-RES-131K
    11. 125985
    Prev
    Next
    INDEX
    Explanations

    geographic locations and place names

    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
     Fuse
    -0.07
    exus
    -0.06
     within
    -0.06
    Ñĩе
    -0.06
    311
    -0.06
     sub
    -0.06
     with
    -0.06
    [d
    -0.05
     organic
    -0.05
     result
    -0.05
    POSITIVE LOGITS
     voks
    0.08
    âĦĸâĦĸ
    0.07
    é±
    0.07
    ÐłÐĿ
    0.07
    eniable
    0.07
    무
    0.07
    ãĤ¿ãĥ³
    0.07
    ysi
    0.07
     HOLDERS
    0.07
    _TRNS
    0.07
    Activations Density 0.073%

    No Known Activations