© 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. 95673
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to events and activities within a community or region

    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
     embedded
    -0.06
     singular
    -0.06
    374
    -0.05
     Gentle
    -0.05
    ìķ¼
    -0.05
    y
    -0.05
     Comp
    -0.05
     Greg
    -0.05
     junk
    -0.05
    ä»ĺ
    -0.05
    POSITIVE LOGITS
    reate
    0.09
    ntax
    0.08
    ocale
    0.08
    rescia
    0.08
    etus
    0.08
     afterwards
    0.08
    vak
    0.08
    ocal
    0.08
    ourcem
    0.07
    ÙijÙħ
    0.07
    Activations Density 0.030%

    No Known Activations