© 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. 77547
    Prev
    Next
    INDEX
    Explanations

    references to personal collections and collecting activities

    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
    _qos
    -0.07
    .mapbox
    -0.07
    rnd
    -0.06
    ź
    -0.06
    cloth
    -0.06
    itere
    -0.06
    ASON
    -0.06
    _DEFINE
    -0.06
    Rs
    -0.06
    RN
    -0.06
    POSITIVE LOGITS
     collectors
    0.14
     collecting
    0.13
     collector
    0.13
    Collect
    0.13
     Collect
    0.12
     collect
    0.12
     collection
    0.12
    collect
    0.12
    collector
    0.11
     Collection
    0.11
    Activations Density 0.057%

    No Known Activations