© 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 EvalsExportsinterp-engineNEWAPI 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. 62507
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and punctuation that indicate conversation

    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
    atz
    -0.07
    ãģªãģĹ
    -0.06
    artz
    -0.05
    apt
    -0.05
     May
    -0.05
     impro
    -0.05
     —
    -0.05
    inka
    -0.05
    isle
    -0.05
    ông
    -0.05
    POSITIVE LOGITS
    iyan
    0.08
    geois
    0.07
    wap
    0.07
    ement
    0.07
    ÙĤاÙħ
    0.07
    ç·Ĵ
    0.07
    quelle
    0.07
    FINE
    0.07
     náp
    0.07
    086
    0.07
    Activations Density 0.013%

    No Known Activations