© 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. 105527
    Prev
    Next
    INDEX
    Explanations

    references to categorized content and posts

    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
    asto
    -0.07
    oha
    -0.07
    è¾ĥ
    -0.07
    ramer
    -0.07
    auen
    -0.07
    åĥ
    -0.06
    ály
    -0.06
    ahoo
    -0.06
    avana
    -0.06
    .tie
    -0.06
    POSITIVE LOGITS
     exact
    0.08
     exactly
    0.07
    .Dictionary
    0.06
     Ley
    0.06
     Bak
    0.06
    Æł
    0.06
    ä¸Ī
    0.06
     strength
    0.06
    icode
    0.06
     treatment
    0.05
    Activations Density 0.001%

    No Known Activations