© 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 EvalsExportsinterp-engineNEWAPI 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. 4952
    Prev
    Next
    INDEX
    Explanations

    expressions indicating predictions or expectations

    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
    ilon
    -0.08
    ivas
    -0.06
    ç³
    -0.06
    æķ¦
    -0.06
    laz
    -0.06
    ZO
    -0.06
    ILON
    -0.06
    icas
    -0.06
    oger
    -0.06
     Tos
    -0.05
    POSITIVE LOGITS
    ÙĤاÙħ
    0.07
     same
    0.07
    SAME
    0.07
    оÑģÑĢед
    0.06
    ÑĮко
    0.06
    bec
    0.06
    Ðİ
    0.06
    itative
    0.06
    cher
    0.06
    881
    0.06
    Activations Density 0.024%

    No Known Activations