© 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 EvalsExportsAPI 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. 106210
    Prev
    Next
    INDEX
    Explanations

    terminology associated with lethal diseases and their effects on animals

    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
    .bz
    -0.09
    trieve
    -0.08
    tember
    -0.08
    artz
    -0.08
    alars
    -0.07
    laus
    -0.07
    .inflate
    -0.07
    alg
    -0.07
    porno
    -0.07
    bz
    -0.07
    POSITIVE LOGITS
    uplic
    0.06
    -collapse
    0.06
     cas
    0.06
    lec
    0.06
     en
    0.06
    gon
    0.06
     r
    0.06
     Victims
    0.06
     Avery
    0.06
     rac
    0.05
    Activations Density 0.008%

    No Known Activations