© 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. 57015
    Prev
    Next
    INDEX
    Explanations

    terms related to user interface elements and toolkits

    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
     пÑĢоÑĢ
    -0.08
    htub
    -0.07
    eck
    -0.07
    aney
    -0.07
    tdown
    -0.07
    Scoped
    -0.07
    樹
    -0.07
    apult
    -0.07
     деÑĢ
    -0.07
    ÑĩеÑĢ
    -0.07
    POSITIVE LOGITS
    ing
    0.10
    bars
    0.08
    ว
    0.07
    mith
    0.07
    266
    0.06
    uff
    0.06
     clang
    0.06
    ivec
    0.06
    EL
    0.06
    idth
    0.06
    Activations Density 0.001%

    No Known Activations