© 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. 77415
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to media and communication

    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
    ieres
    -0.09
    @nate
    -0.08
    POSIT
    -0.08
    é§ħå¾ĴæŃ©
    -0.07
    inish
    -0.07
    edback
    -0.07
    omik
    -0.07
    rame
    -0.07
    ylül
    -0.07
    à¸Ńà¹Ģร
    -0.07
    POSITIVE LOGITS
     usually
    0.07
     often
    0.07
     ("
    0.06
     either
    0.06
    iterr
    0.06
     trope
    0.06
     Either
    0.06
     sob
    0.05
    usually
    0.05
     may
    0.05
    Activations Density 0.001%

    No Known Activations