© 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 EvalsExportsAPI 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. 88934
    Prev
    Next
    INDEX
    Explanations

    references to positional measurements and coordinates

    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
    znik
    -0.09
    OfSize
    -0.07
    atra
    -0.07
    าà¸ĵ
    -0.07
    wig
    -0.07
    @show
    -0.07
    à¸ļà¸Ĺ
    -0.07
    ablo
    -0.07
    plet
    -0.07
    abr
    -0.07
    POSITIVE LOGITS
     position
    0.10
    position
    0.09
     relative
    0.08
    .position
    0.08
    ä½įç½®
    0.08
    -position
    0.08
    RelativeTo
    0.07
     location
    0.07
     Position
    0.07
     place
    0.07
    Activations Density 0.079%

    No Known Activations