© 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. 42221
    Prev
    Next
    INDEX
    Explanations

    words related to visual elements and design qualities

    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
    owler
    -0.08
    inke
    -0.07
    agini
    -0.07
    plier
    -0.07
    ozor
    -0.07
    obia
    -0.07
    ipi
    -0.07
    IFORM
    -0.07
    pyx
    -0.07
    dÄĽ
    -0.07
    POSITIVE LOGITS
     im
    0.06
     setattr
    0.06
    tte
    0.06
     ferr
    0.06
    èģ
    0.06
    ìłķìĿ´
    0.06
     this
    0.06
     Tender
    0.06
    125
    0.06
    abor
    0.06
    Activations Density 0.000%

    No Known Activations