© 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 EvalsExportsinterp-engineNEWAPI 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. 2425
    Prev
    Next
    INDEX
    Explanations

    references to previous or revised versions of content

    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
    itters
    -0.06
    473
    -0.06
     Cass
    -0.06
    ký
    -0.06
     æļ
    -0.05
     оглÑı
    -0.05
    eries
    -0.05
    781
    -0.05
     appDelegate
    -0.05
    çĶ²
    -0.05
    POSITIVE LOGITS
    /original
    0.08
    getDisplay
    0.07
     NEGLIGENCE
    0.07
    ElementsBy
    0.07
    elper
    0.07
    .this
    0.07
     intox
    0.07
    iglia
    0.07
    -article
    0.07
    adow
    0.07
    Activations Density 0.004%

    No Known Activations