© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14364
    Prev
    Next
    INDEX
    Explanations

    the phrase "within" and its variations, indicating a focus on internal perspectives or 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
    ÑĤÑİ
    -0.09
    족
    -0.08
    yat
    -0.08
    yk
    -0.08
    زÙĪ
    -0.08
    алÑİ
    -0.08
    ses
    -0.08
    edback
    -0.08
    -scrollbar
    -0.08
    ÑĩÑĥк
    -0.08
    POSITIVE LOGITS
    most
    0.09
    creasing
    0.09
    /out
    0.09
    st
    0.08
     bounds
    0.08
    -
    0.07
    -the
    0.07
    673
    0.07
    603
    0.07
     confines
    0.07
    Activations Density 0.023%

    No Known Activations