© 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. 27987
    Prev
    Next
    INDEX
    Explanations

    phrases indicating presence and status of items or subjects

    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
    ureau
    -0.07
    oller
    -0.06
    ohan
    -0.06
    odb
    -0.06
    udeau
    -0.06
     Lust
    -0.06
    boat
    -0.06
    adol
    -0.06
    iera
    -0.06
     Narrow
    -0.06
    POSITIVE LOGITS
    chg
    0.09
     Markus
    0.07
    ëŀĺ
    0.07
    ÙĥÙĬÙĦ
    0.07
    678
    0.07
    ãĥ³ãĥĶ
    0.06
    á»ĥ
    0.06
    ави
    0.06
     Shades
    0.06
    лиÑĤ
    0.06
    Activations Density 0.005%

    No Known Activations