© 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. 118709
    Prev
    Next
    INDEX
    Explanations

    instances of text or symbols significant in various cultural contexts

    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
    thinkable
    -0.07
    abel
    -0.06
    usc
    -0.06
     Institutes
    -0.06
    joy
    -0.06
    CHASE
    -0.06
    iero
    -0.06
    mind
    -0.06
    inez
    -0.06
    achen
    -0.06
    POSITIVE LOGITS
    emm
    0.07
    oker
    0.07
    _inches
    0.07
    ÃŃl
    0.07
    -sizing
    0.07
    ï¸
    0.07
    ix
    0.06
    aload
    0.06
    affer
    0.06
    loff
    0.06
    Activations Density 0.001%

    No Known Activations