© 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. 84700
    Prev
    Next
    INDEX
    Explanations

    corporate or brand names within the text

    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
    $MESS
    -0.08
    $LANG
    -0.07
    ordo
    -0.07
    ksen
    -0.07
    -deals
    -0.07
    žen
    -0.07
    /disable
    -0.07
    feeds
    -0.07
     reorder
    -0.06
    jah
    -0.06
    POSITIVE LOGITS
     Santo
    0.07
     Perkins
    0.06
    wik
    0.06
    imas
    0.06
    -
    0.06
    &s
    0.06
    irs
    0.06
    ä½³
    0.05
    scan
    0.05
     Duffy
    0.05
    Activations Density 0.029%

    No Known Activations