© 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. 16411
    Prev
    Next
    INDEX
    Explanations

    numerical data related to events and statistics

    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
    anean
    -0.07
    eper
    -0.07
    afe
    -0.07
    forme
    -0.07
    aland
    -0.07
    ughs
    -0.06
    adelphia
    -0.06
    ause
    -0.06
     Cout
    -0.06
     ob
    -0.06
    POSITIVE LOGITS
    ÑĪка
    0.07
    Template
    0.06
    (es
    0.06
    ÄĽtÅ¡
    0.06
     Template
    0.06
    ADX
    0.06
    çŀ
    0.06
    иж
    0.06
    rij
    0.06
    MSN
    0.06
    Activations Density 0.001%

    No Known Activations