© 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. 15-LLAMASCOPE-RES-131K
    11. 27143
    Prev
    Next
    INDEX
    Explanations

    references to holsters and related accessories

    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
    erli
    -0.07
    à¥ģद
    -0.06
    ANJI
    -0.06
    bia
    -0.06
    972
    -0.06
     Invitation
    -0.06
     Superintendent
    -0.06
    éĺ¶
    -0.06
    coder
    -0.06
    ãģĵãĤĵ
    -0.06
    POSITIVE LOGITS
    opis
    0.06
    elps
    0.06
     Stealth
    0.06
     Breed
    0.06
    YSTEM
    0.06
    ookie
    0.06
     straps
    0.06
     Nah
    0.06
     деÑĢж
    0.06
    Serialized
    0.06
    Activations Density 0.001%

    No Known Activations