© 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. 106735
    Prev
    Next
    INDEX
    Explanations

    references to birds and feeding them

    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
     mapping
    -0.07
    Mapping
    -0.06
    mapping
    -0.06
    iglia
    -0.06
    ROP
    -0.06
    _mapping
    -0.06
    -0.06
     Mapping
    -0.06
     breath
    -0.06
     nit
    -0.06
    POSITIVE LOGITS
     feed
    0.09
     feeding
    0.08
     feeder
    0.08
    -feed
    0.08
     коÑĢм
    0.08
    Feed
    0.08
     ì²ł
    0.08
    .feed
    0.08
     bird
    0.08
    aptor
    0.08
    Activations Density 0.013%

    No Known Activations