© 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. 80594
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion or difficulty with problems

    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
    ISC
    -0.07
    Stamped
    -0.06
    Stamp
    -0.06
    nap
    -0.06
    une
    -0.06
    наÑĤ
    -0.06
    esis
    -0.06
    ÙĨدÙĤ
    -0.06
    ắc
    -0.06
    θεί
    -0.06
    POSITIVE LOGITS
     how
    0.07
     when
    0.06
    adaki
    0.06
     trying
    0.06
     nonatomic
    0.06
    ÐĶÐIJ
    0.06
    ypad
    0.05
     Lau
    0.05
    assed
    0.05
    以ä¸ĭ
    0.05
    Activations Density 0.007%

    No Known Activations