© 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. 27562
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and associated movements or actions

    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
    central
    -0.07
    hta
    -0.07
    uard
    -0.07
    iciones
    -0.06
    antom
    -0.06
    _DP
    -0.06
     intermediate
    -0.06
    apt
    -0.06
    abei
    -0.06
     DeepCopy
    -0.06
    POSITIVE LOGITS
     border
    0.21
     Border
    0.18
    border
    0.17
     BORDER
    0.16
    Border
    0.15
     borders
    0.14
    -border
    0.14
    _border
    0.12
    .border
    0.12
    	border
    0.11
    Activations Density 0.092%

    No Known Activations