© 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. 84541
    Prev
    Next
    INDEX
    Explanations

    phrases related to user-friendly software and ease of use

    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
    arty
    -0.07
    AMED
    -0.07
    ESH
    -0.07
    phies
    -0.07
    rame
    -0.07
    edes
    -0.07
    ixer
    -0.07
    иÑĩна
    -0.06
    edb
    -0.06
    dens
    -0.06
    POSITIVE LOGITS
    ify
    0.07
     interface
    0.07
    /manage
    0.07
    ability
    0.07
    /simple
    0.06
    implify
    0.06
    ono
    0.06
    heit
    0.06
    fragistics
    0.06
    ignon
    0.06
    Activations Density 0.009%

    No Known Activations