© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96240
    Prev
    Next
    INDEX
    Explanations

    references to additional content or prompts to read more

    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
    er
    -0.07
     h
    -0.07
     â
    -0.06
     j
    -0.06
    acc
    -0.06
     (
    -0.06
     can
    -0.06
     Ãĥ
    -0.06
    at
    -0.06
     n
    -0.05
    POSITIVE LOGITS
    ACHE
    0.08
    िड
    0.08
    برد
    0.08
    ocuk
    0.08
    HEMA
    0.08
    elsen
    0.07
    eyse
    0.07
    ibri
    0.07
     GDK
    0.07
    pNet
    0.07
    Activations Density 0.029%

    No Known Activations