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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 44159
    Prev
    Next
    INDEX
    Explanations

    syntax related to programming or configuration files

    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
     fauc
    -0.06
    oice
    -0.06
    axon
    -0.06
    warts
    -0.06
    cil
    -0.06
     pill
    -0.05
    pong
    -0.05
    andon
    -0.05
    KeyId
    -0.05
    ifton
    -0.05
    POSITIVE LOGITS
     dirname
    0.12
    (real
    0.11
    real
    0.11
     realpath
    0.11
    dirname
    0.11
     DIRECTORY
    0.10
     real
    0.10
    _VENDOR
    0.10
     vendor
    0.10
     Vendor
    0.10
    Activations Density 0.006%

    No Known Activations