© 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. 76926
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory terms and 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
     addCriterion
    -0.06
    andel
    -0.06
    -urlencoded
    -0.06
    igne
    -0.06
    ikip
    -0.06
    getManager
    -0.06
    ide
    -0.06
    book
    -0.05
     sake
    -0.05
    ogan
    -0.05
    POSITIVE LOGITS
     helf
    0.07
    /Set
    0.07
    ken
    0.07
     sett
    0.07
    _ASSUME
    0.07
     Ñģло
    0.06
    bart
    0.06
    기ëıĦ
    0.06
     consumer
    0.06
    amilia
    0.06
    Activations Density 0.000%

    No Known Activations