© 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. 71040
    Prev
    Next
    INDEX
    Explanations

    statistical references and descriptors related to demographics

    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
    errar
    -0.06
    -turned
    -0.06
    eno
    -0.06
    NEY
    -0.06
     endwhile
    -0.05
    ccoli
    -0.05
    quartered
    -0.05
    âĢ¦↵
    -0.05
    erca
    -0.05
    omore
    -0.05
    POSITIVE LOGITS
    oice
    0.07
    otos
    0.07
     modal
    0.07
    vÃŃ
    0.07
     median
    0.07
    OfYear
    0.07
    vip
    0.07
    æĤł
    0.07
    igure
    0.06
    uras
    0.06
    Activations Density 0.004%

    No Known Activations