© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16473
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to origin or source

    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
    frei
    -0.08
     discrepan
    -0.07
    ãģ¡ãģ¯
    -0.07
    OID
    -0.07
    ault
    -0.07
    getApplication
    -0.07
    anja
    -0.07
    acija
    -0.07
    alte
    -0.06
    ãĥ«ãĥĪ
    -0.06
    POSITIVE LOGITS
     elsewhere
    0.08
     previous
    0.08
     previously
    0.07
     overseas
    0.07
    istent
    0.06
    else
    0.06
     khá»ıi
    0.06
     Else
    0.06
    previous
    0.06
    gis
    0.06
    Activations Density 0.016%

    No Known Activations