© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 73457
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "a" in different contexts

    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
    ades
    -0.07
    gratis
    -0.06
    aggable
    -0.06
    éĿł
    -0.06
    edes
    -0.06
    AINS
    -0.06
    è£ı
    -0.06
    ifton
    -0.06
    edBy
    -0.06
     collateral
    -0.06
    POSITIVE LOGITS
    ancies
    0.07
    .synthetic
    0.06
    ÑĢÑĥб
    0.06
    iego
    0.06
    itere
    0.06
     Said
    0.06
    Ñħодим
    0.06
     Barn
    0.06
    ecz
    0.06
     бÑĭ
    0.06
    Activations Density 0.001%

    No Known Activations