© 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. 30195
    Prev
    Next
    INDEX
    Explanations

    ellipses and other forms of textual indicators that suggest omission or continuation

    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
    ÄĽr
    -0.06
    848
    -0.06
    ooter
    -0.06
    usher
    -0.06
    ãģ¨ãģį
    -0.06
     Ranch
    -0.05
    573
    -0.05
    690
    -0.05
     Weiss
    -0.05
    951
    -0.05
    POSITIVE LOGITS
     suy
    0.08
    ãĥ¼ãĥĨãĤ£
    0.07
    kas
    0.07
    quiv
    0.07
    venes
    0.07
    ButtonType
    0.07
    знаÑĩа
    0.07
    'er
    0.07
    nerg
    0.07
    yna
    0.07
    Activations Density 0.004%

    No Known Activations