© 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. 117106
    Prev
    Next
    INDEX
    Explanations

    references to military or strategic locations and operations

    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
    icha
    -0.08
    rana
    -0.07
    ccione
    -0.07
    otta
    -0.07
     Hüs
    -0.06
    غÙĨ
    -0.06
    uhl
    -0.06
    reon
    -0.06
    anki
    -0.06
    orget
    -0.06
    POSITIVE LOGITS
     established
    0.08
     camp
    0.08
    گاÙĩ
    0.07
    /base
    0.07
     base
    0.07
     Camp
    0.07
     located
    0.07
    site
    0.07
    ibase
    0.07
    ovacÃŃ
    0.07
    Activations Density 0.049%

    No Known Activations