© 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. 54068
    Prev
    Next
    INDEX
    Explanations

    references to song titles and their descriptions

    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
    IMIT
    -0.07
    unos
    -0.06
    unga
    -0.06
     redraw
    -0.06
     coverage
    -0.06
    olf
    -0.06
    isser
    -0.06
     Coverage
    -0.05
    icana
    -0.05
    ubl
    -0.05
    POSITIVE LOGITS
    aghan
    0.07
    orado
    0.07
    ulen
    0.07
    Sink
    0.07
    pite
    0.07
    antu
    0.07
     apt
    0.07
    #
    0.07
    olla
    0.07
     CLUB
    0.07
    Activations Density 0.028%

    No Known Activations