© 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. 86755
    Prev
    Next
    INDEX
    Explanations

    spatial and cultural connections between different backgrounds and locations

    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
    avec
    -0.07
     åĪ°
    -0.07
    åĪ°
    -0.07
    ifs
    -0.07
    vÃŃc
    -0.07
    Abs
    -0.07
    jec
    -0.07
    entai
    -0.07
    alles
    -0.07
    aln
    -0.07
    POSITIVE LOGITS
     sources
    0.11
     backgrounds
    0.10
     elsewhere
    0.10
     nowhere
    0.10
    sources
    0.09
     background
    0.09
     from
    0.09
     Sources
    0.08
    from
    0.08
     source
    0.08
    Activations Density 0.066%

    No Known Activations