© 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. 16323
    Prev
    Next
    INDEX
    Explanations

    specific numerical values related to data or statistics

    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
    tuÄŁ
    -0.06
    oise
    -0.06
    оÑĢе
    -0.06
    окÑĢем
    -0.06
    ÐĦ
    -0.06
    δÏĮ
    -0.06
    lector
    -0.06
    isku
    -0.06
    Orth
    -0.06
    ieg
    -0.06
    POSITIVE LOGITS
    strup
    0.07
    amar
    0.07
    ivet
    0.06
    aleigh
    0.06
    iling
    0.06
    ":""
    0.06
    ensburg
    0.06
     гÑĢÑĥ
    0.06
    etable
    0.06
     åħŃ
    0.06
    Activations Density 0.044%

    No Known Activations