© 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. 15-LLAMASCOPE-RES-131K
    11. 88598
    Prev
    Next
    INDEX
    Explanations

    information related to measurements and time frames

    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
    zburg
    -0.08
    aliz
    -0.08
    itung
    -0.07
    eless
    -0.07
    rar
    -0.07
    agli
    -0.07
     Isles
    -0.07
    inati
    -0.07
    rame
    -0.07
    jah
    -0.07
    POSITIVE LOGITS
    Æ°
    0.07
     respectively
    0.07
    .each
    0.06
    bserv
    0.06
     each
    0.06
    ISTA
    0.06
    ãģĿãĤĮ
    0.06
     FI
    0.05
     Bennett
    0.05
     cada
    0.05
    Activations Density 0.035%

    No Known Activations