© 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. 40285
    Prev
    Next
    INDEX
    Explanations

    citations and references from academic articles

    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
    .tom
    -0.09
     Sinn
    -0.08
    avra
    -0.08
     prav
    -0.07
    morgan
    -0.07
    ýt
    -0.07
    ëħ
    -0.07
    ảo
    -0.07
     ÙĪاÙĦØ¥
    -0.07
    .LayoutStyle
    -0.07
    POSITIVE LOGITS
     porter
    0.06
     buff
    0.06
     punct
    0.06
    iw
    0.05
     in
    0.05
    ert
    0.05
    uch
    0.05
     jo
    0.05
    j
    0.05
    oro
    0.05
    Activations Density 0.010%

    No Known Activations