Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96010
    Prev
    Next
    INDEX
    Explanations

    quoted speech or statements

    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
    omer
    -0.06
     Eph
    -0.06
    omers
    -0.06
    anter
    -0.06
    ãĥ¼ãĥ«ãĥī
    -0.06
     Bol
    -0.06
    oth
    -0.05
     Hung
    -0.05
    rell
    -0.05
     LA
    -0.05
    POSITIVE LOGITS
    ãĥ«ãĤ¯
    0.07
    bsite
    0.07
    lick
    0.07
     çŁ³
    0.07
     Klo
    0.07
     hrom
    0.07
    eks
    0.07
    okud
    0.06
    ì¹
    0.06
     ç±
    0.06
    Activations Density 0.017%

    No Known Activations