Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5298
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical conductivity and its various properties

    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
    erais
    -0.08
    ноÑģÑıÑĤ
    -0.08
    ervers
    -0.07
    arch
    -0.07
    arching
    -0.07
    iling
    -0.07
    bery
    -0.07
    acey
    -0.07
    _cons
    -0.07
    tings
    -0.06
    POSITIVE LOGITS
    ors
    0.10
    eur
    0.10
    ance
    0.09
    ive
    0.07
    icut
    0.07
    ivities
    0.07
    ivity
    0.07
    eam
    0.06
    ickle
    0.06
    uala
    0.06
    Activations Density 0.008%

    No Known Activations