© 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. 87769
    Prev
    Next
    INDEX
    Explanations

    instances of authorship or attribution

    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
    estre
    -0.07
    rowned
    -0.07
    ClickListener
    -0.07
    enberg
    -0.07
    usta
    -0.07
    uforia
    -0.07
    iasm
    -0.06
     iddi
    -0.06
    ppard
    -0.06
    aname
    -0.06
    POSITIVE LOGITS
    archy
    0.07
    BOTTOM
    0.07
    vig
    0.06
    ANGED
    0.06
     inf
    0.06
    haven
    0.06
    δα
    0.06
    ữ
    0.06
    ÑĥнкÑĤ
    0.06
     Hacker
    0.06
    Activations Density 0.000%

    No Known Activations