© 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. 126224
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and their associated URLs

    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
     Gan
    -0.07
     std
    -0.06
    æIJŃ
    -0.06
    unda
    -0.06
     Flow
    -0.06
    Default
    -0.06
    keterangan
    -0.06
     Fund
    -0.06
     DISCLAIMER
    -0.06
    ÑĤап
    -0.06
    POSITIVE LOGITS
    CJK
    0.08
    .SizeType
    0.08
     ar
    0.08
    /Typography
    0.08
    icontrol
    0.07
    iaux
    0.07
    -paper
    0.07
     paper
    0.07
    laden
    0.07
    üre
    0.07
    Activations Density 0.010%

    No Known Activations