© 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. 41608
    Prev
    Next
    INDEX
    Explanations

    elements related to academic citations and publication details

    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
     sscanf
    -0.06
    784
    -0.06
    _texts
    -0.06
    Ä±ÅŁÄ±
    -0.06
     Audit
    -0.06
    å¹²
    -0.06
    ansi
    -0.06
    404
    -0.06
    Ñģли
    -0.06
    dere
    -0.06
    POSITIVE LOGITS
    ailable
    0.09
    ObjectContext
    0.07
    nia
    0.07
    cü
    0.07
    swick
    0.06
    upp
    0.06
    inja
    0.06
    ilate
    0.06
    ADER
    0.06
    gio
    0.06
    Activations Density 0.010%

    No Known Activations