© 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. 9-LLAMASCOPE-RES-131K
    11. 98923
    Prev
    Next
    INDEX
    Explanations

    terms related to vinyl and its applications or properties

    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
    ients
    -0.07
    idges
    -0.07
    endor
    -0.06
    abouts
    -0.06
     Remed
    -0.06
    places
    -0.05
    enheim
    -0.05
     Fuse
    -0.05
    ching
    -0.05
    ollo
    -0.05
    POSITIVE LOGITS
    ldr
    0.07
    atego
    0.07
    ERRUPT
    0.07
    estroy
    0.07
    ized
    0.07
    tember
    0.07
    bian
    0.07
    ahoo
    0.07
    anness
    0.07
    ên
    0.07
    Activations Density 0.003%

    No Known Activations