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

    Neuronpedia

    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. 58169
    Prev
    Next
    INDEX
    Explanations

    instances of formal or professional titles and roles

    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
    ideographic
    -0.07
    antha
    -0.07
    ene
    -0.07
    ERCHANT
    -0.07
    GMEM
    -0.07
    heim
    -0.07
    ahlen
    -0.07
    aze
    -0.06
    ething
    -0.06
     гоÑĤ
    -0.06
    POSITIVE LOGITS
     later
    0.06
     was
    0.06
     latter
    0.06
    бо
    0.06
    was
    0.06
     briefly
    0.06
     similarly
    0.06
    rof
    0.06
    ITT
    0.06
     Dit
    0.06
    Activations Density 0.017%

    No Known Activations