© 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. 129084
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal citations and associated numerical data

    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
     disb
    -0.06
     bur
    -0.06
     Disclaimer
    -0.05
    Äĥn
    -0.05
    hq
    -0.05
    PRS
    -0.05
     verm
    -0.05
     brun
    -0.05
     (
    -0.05
     civil
    -0.05
    POSITIVE LOGITS
    _tE
    0.08
    @qq
    0.08
    _tA
    0.08
    -slide
    0.07
     Hüs
    0.07
    ranÃŃ
    0.07
    ëŀ
    0.07
    ocker
    0.07
    /authentication
    0.07
    /goto
    0.07
    Activations Density 0.006%

    No Known Activations