© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75131
    Prev
    Next
    INDEX
    Explanations

    elements related to storytelling in various media

    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
    lov
    -0.07
    tech
    -0.06
    _nat
    -0.06
     newly
    -0.06
     transparent
    -0.06
    702
    -0.06
     Incoming
    -0.05
    -transparent
    -0.05
    (.)
    -0.05
    ë°©
    -0.05
    POSITIVE LOGITS
    iyat
    0.08
    Unmarshaller
    0.08
    eza
    0.07
    gid
    0.07
    ispecies
    0.07
    sembly
    0.07
    viso
    0.07
    .Interop
    0.07
    sembl
    0.07
    rz
    0.07
    Activations Density 0.031%

    No Known Activations