© 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. 41951
    Prev
    Next
    INDEX
    Explanations

    references to dimensions and dimensionality in various contexts

    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
    anto
    -0.08
    ork
    -0.08
    ress
    -0.07
    roll
    -0.07
    ive
    -0.07
    dy
    -0.07
    ython
    -0.07
    yn
    -0.07
    orio
    -0.07
    avis
    -0.07
    POSITIVE LOGITS
    ality
    0.15
    ally
    0.11
    nal
    0.09
    less
    0.09
    ize
    0.08
    ized
    0.08
    nement
    0.08
    als
    0.08
    度
    0.08
    ention
    0.07
    Activations Density 0.020%

    No Known Activations