© 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. 106569
    Prev
    Next
    INDEX
    Explanations

    references to errors and misunderstandings

    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
    isphere
    -0.07
    ulur
    -0.07
    ieres
    -0.07
    throw
    -0.06
    allon
    -0.06
    orge
    -0.06
    819
    -0.06
    ennon
    -0.06
    rane
    -0.06
    miner
    -0.06
    POSITIVE LOGITS
    ingly
    0.12
    ably
    0.08
    uous
    0.08
    ellan
    0.07
    ously
    0.07
    gré
    0.07
    /false
    0.07
    .metamodel
    0.06
    kus
    0.06
    pecies
    0.06
    Activations Density 0.006%

    No Known Activations