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. 9-LLAMASCOPE-RES-131K
    6. 96078
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to computational or algorithmic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    neural activity related to describing spatial loadings, sampling, and modeling fields in scientific or technical contexts.

    oai_token-act-pair · gpt-4.1-nanoTriggered by @belindazli65
    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
    /mainwindow
    -0.07
    /gui
    -0.07
    PIPE
    -0.07
    oras
    -0.07
    ç¾
    -0.07
    ucer
    -0.07
     klu
    -0.07
    (=)
    -0.07
    nett
    -0.06
    étique
    -0.06
    POSITIVE LOGITS
     Unlock
    0.06
    CKET
    0.06
    ived
    0.06
     Fat
    0.05
     Fond
    0.05
     McC
    0.05
    mont
    0.05
     Fowler
    0.05
     Liberties
    0.05
     spotlight
    0.05
    Activations Density 0.049%

    No Known Activations