© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85633
    Prev
    Next
    INDEX
    Explanations

    web links and hyperlinks

    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
    anes
    -0.06
    anst
    -0.06
    ansom
    -0.06
    licit
    -0.06
    ans
    -0.06
    ancock
    -0.06
    lip
    -0.06
    leo
    -0.05
    анÑģ
    -0.05
    overs
    -0.05
    POSITIVE LOGITS
    uzzi
    0.08
    GetString
    0.07
    etta
    0.07
    YPRE
    0.07
    -thumbnail
    0.07
    ilor
    0.07
     pregn
    0.07
    ãĤĩ
    0.07
     Wort
    0.07
    ifact
    0.07
    Activations Density 0.002%

    No Known Activations