© 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. 77088
    Prev
    Next
    INDEX
    Explanations

    negative phrases and expressions

    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
    ÃŃn
    -0.06
     Hir
    -0.06
    aving
    -0.06
    invert
    -0.06
     playable
    -0.06
    len
    -0.06
     distract
    -0.06
    ffen
    -0.06
    ented
    -0.06
    iros
    -0.06
    POSITIVE LOGITS
     hesitate
    0.09
     hes
    0.07
    gfx
    0.06
    ÑħÑĥ
    0.06
    .GraphicsUnit
    0.06
    åªĴ
    0.06
    .SizeType
    0.06
     dziew
    0.06
     Orta
    0.06
     Vladim
    0.06
    Activations Density 0.003%

    No Known Activations