© 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. 84122
    Prev
    Next
    INDEX
    Explanations

    contexts and instances related to specific cases or scenarios

    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
    313
    -0.07
    enth
    -0.07
     Decomp
    -0.06
    ing
    -0.06
    imits
    -0.06
    lich
    -0.06
    кÑĥÑĤ
    -0.06
    άβ
    -0.06
    epar
    -0.06
     Richardson
    -0.06
    POSITIVE LOGITS
    -ci
    0.08
    punkt
    0.07
    AppName
    0.07
    aina
    0.07
    ,
    0.06
    AIN
    0.06
    751
    0.06
    agua
    0.06
    anlı
    0.06
    icular
    0.06
    Activations Density 0.009%

    No Known Activations