© 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. 77216
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicative of sentence structure

    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
     ph
    -0.06
     means
    -0.06
     J
    -0.06
    Õ¡
    -0.06
    uer
    -0.06
     true
    -0.06
    798
    -0.06
     Phelps
    -0.06
    branch
    -0.05
    stood
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    //{{
    0.09
    (íģ¬ê¸°
    0.08
    #ga
    0.08
    RuleContext
    0.08
    hoo
    0.08
    #aa
    0.07
    _CURSOR
    0.07
    íĨłíĨł
    0.07
    OptionsResolver
    0.07
    Activations Density 0.001%

    No Known Activations