© 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. 29704
    Prev
    Next
    INDEX
    Explanations

    non-verbal elements and formatting in text

    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
    _excerpt
    -0.07
    lém
    -0.06
    MBProgressHUD
    -0.06
    ï¼Īå¹³æĪIJ
    -0.06
     Abort
    -0.06
    @email
    -0.06
     Edmonton
    -0.06
    .Emit
    -0.06
     Oilers
    -0.06
     cih
    -0.06
    POSITIVE LOGITS
     NY
    0.11
     NYC
    0.11
    NY
    0.10
     New
    0.09
     Manhattan
    0.08
    New
    0.08
     NYPD
    0.07
     ny
    0.07
     NJ
    0.07
    ç´
    0.07
    Activations Density 0.000%

    No Known Activations