© 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. 126893
    Prev
    Next
    INDEX
    Explanations

    information about social behavior and mating patterns in animal species

    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
    phylum
    -0.09
    amble
    -0.07
    omnia
    -0.07
    urette
    -0.07
    usz
    -0.07
     Fuse
    -0.06
    ounty
    -0.06
    RATE
    -0.06
    563
    -0.06
    еÑı
    -0.06
    POSITIVE LOGITS
     territor
    0.07
     Playback
    0.07
     GOODMAN
    0.07
     Territory
    0.06
     intra
    0.06
    sen
    0.06
     females
    0.06
     cached
    0.06
     Cached
    0.06
     пÑĢип
    0.06
    Activations Density 0.021%

    No Known Activations