© 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 EvalsExportsinterp-engineNEWAPI 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. 80088
    Prev
    Next
    INDEX
    Explanations

    key nouns and their associations related to central characters and plot elements in a narrative

    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
    prung
    -0.08
    Elf
    -0.07
     $č↵
    -0.07
     Elf
    -0.07
    ngrx
    -0.06
    ivet
    -0.06
    .setdefault
    -0.06
     insn
    -0.06
    bish
    -0.06
    biased
    -0.06
    POSITIVE LOGITS
     Benton
    0.07
    Power
    0.07
     Power
    0.07
     power
    0.06
    erver
    0.06
    power
    0.06
    ieten
    0.06
    ians
    0.06
     Lock
    0.06
     appended
    0.06
    Activations Density 0.002%

    No Known Activations