© 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. 95575
    Prev
    Next
    INDEX
    Explanations

    references to compiler-generated code and structures

    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
    reds
    -0.07
    hiba
    -0.07
    ÑĩаÑĤ
    -0.07
    omik
    -0.07
     Yus
    -0.06
    imm
    -0.06
    OUCH
    -0.06
    üs
    -0.06
    å½¹
    -0.06
    rij
    -0.06
    POSITIVE LOGITS
     Vern
    0.07
    atic
    0.06
    Fuse
    0.06
     ab
    0.06
    istring
    0.06
    å¼ı
    0.06
    Invariant
    0.06
    CTS
    0.06
    .ManyToMany
    0.06
    uchsia
    0.06
    Activations Density 0.000%

    No Known Activations