© 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. 9-LLAMASCOPE-RES-131K
    11. 95624
    Prev
    Next
    INDEX
    Explanations

    references to significant solo projects or large undertakings

    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
    rah
    -0.08
     ilma
    -0.07
     discord
    -0.06
    leh
    -0.06
    CSI
    -0.06
    oth
    -0.06
    celed
    -0.06
    YYY
    -0.06
    ictim
    -0.06
    ttp
    -0.06
    POSITIVE LOGITS
    ildo
    0.07
    datable
    0.07
    hend
    0.07
    hor
    0.07
    burg
    0.07
    ereo
    0.06
    enga
    0.06
    гоÑĢ
    0.06
    mium
    0.06
    CustomLabel
    0.06
    Activations Density 0.000%

    No Known Activations