© 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. 95607
    Prev
    Next
    INDEX
    Explanations

    numerical and historical references related to events or notable figures

    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
    angen
    -0.07
    aleza
    -0.07
    rette
    -0.07
    igen
    -0.06
    raith
    -0.06
     ë°©
    -0.06
    rett
    -0.06
    å·±
    -0.06
    è
    -0.06
    readcr
    -0.06
    POSITIVE LOGITS
    çĮ
    0.07
    ãĤ¥
    0.07
    à¥įà¤
    0.07
    ELLOW
    0.07
    enschaft
    0.07
    jas
    0.07
    LTR
    0.06
    çIJ
    0.06
     Ced
    0.06
     gated
    0.06
    Activations Density 0.001%

    No Known Activations