© 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. 118602
    Prev
    Next
    INDEX
    Explanations

    URLs and email addresses associated with organizations

    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
     ún
    -0.07
     اÙĦرÙħزÙĬØ©
    -0.07
    chimp
    -0.06
    afil
    -0.06
    ẻ
    -0.06
    inclu
    -0.06
    ÑĪÑĤ
    -0.06
     بÙĨا
    -0.06
    Ìģt
    -0.06
    rung
    -0.06
    POSITIVE LOGITS
    ://
    0.07
    akes
    0.07
    IENT
    0.06
    ocols
    0.06
    417
    0.06
    ↵↵
    0.06
    owing
    0.06
     Tut
    0.06
    427
    0.06
    ocities
    0.06
    Activations Density 0.010%

    No Known Activations