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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 59886
    Prev
    Next
    INDEX
    Explanations

    items related to numeric or quantitative data representation

    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
    .Localization
    -0.07
    ingu
    -0.07
    lä
    -0.07
     Barber
    -0.07
    leston
    -0.06
    fq
    -0.06
    inge
    -0.06
    lucent
    -0.06
    нÑĤ
    -0.06
     babys
    -0.06
    POSITIVE LOGITS
    olik
    0.07
    amu
    0.06
     left
    0.06
    HEMA
    0.06
     second
    0.06
    aida
    0.06
    iban
    0.06
    икÑĥ
    0.06
     ener
    0.06
     adj
    0.06
    Activations Density 0.008%

    No Known Activations