© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84376
    Prev
    Next
    INDEX
    Explanations

    references to fishing activities and related services in West Virginia

    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
    stagram
    -0.08
    ntag
    -0.07
     yere
    -0.07
    hydr
    -0.07
    indrical
    -0.06
    heiten
    -0.06
    orks
    -0.06
    viously
    -0.06
    едеÑĢа
    -0.06
    amarin
    -0.06
    POSITIVE LOGITS
    200
    0.06
     downloadable
    0.06
     "...
    0.06
    åĪĩ
    0.06
    'n
    0.06
    475
    0.06
     Yahoo
    0.06
    loha
    0.06
     recreated
    0.06
     Ãĥ
    0.06
    Activations Density 0.014%

    No Known Activations