© 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. 94255
    Prev
    Next
    INDEX
    Explanations

    mentions of software licensing and organizational entities

    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
    jong
    -0.07
    216
    -0.07
    anki
    -0.06
    etooth
    -0.06
    787
    -0.06
     brain
    -0.06
    awan
    -0.05
     punct
    -0.05
    ucci
    -0.05
     bip
    -0.05
    POSITIVE LOGITS
    qw
    0.07
     SLOT
    0.07
     æĻ´
    0.07
     Crest
    0.06
    COND
    0.06
    ç½²
    0.06
    ÑĩиÑģл
    0.06
    ela
    0.06
    .scalablytyped
    0.06
     Shades
    0.06
    Activations Density 0.001%

    No Known Activations