© 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. 17-LLAMASCOPE-RES-131K
    11. 71020
    Prev
    Next
    INDEX
    Explanations

    quantitative data or metrics

    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
    ious
    -0.07
    ĥ
    -0.06
    issing
    -0.06
    hab
    -0.06
    à¹Ħว
    -0.06
    ómo
    -0.06
    awning
    -0.06
    imulator
    -0.06
    ãģ£ãģ¡
    -0.06
    apot
    -0.05
    POSITIVE LOGITS
    \xff
    0.07
    dae
    0.06
    Fresh
    0.06
    erk
    0.06
    APT
    0.06
    ingham
    0.06
    Æ°á»Ŀng
    0.06
    çĦ
    0.06
    ãĤ¼
    0.06
     Geh
    0.06
    Activations Density 0.041%

    No Known Activations