© 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. 77125
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods, which may indicate the end of sentences

    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
     Thu
    -0.06
    :
    -0.06
    -
    -0.06
     _
    -0.06
    arked
    -0.06
    /
    -0.06
     import
    -0.06
    "
    -0.06
     meaning
    -0.06
    ↵
    -0.05
    POSITIVE LOGITS
    #af
    0.09
    AdapterManager
    0.08
    @nate
    0.08
    BuilderInterface
    0.08
    opens
    0.08
     æĪĸ
    0.08
    ê±°ëĤĺ
    0.08
    dım
    0.08
    atore
    0.08
    GenerationStrategy
    0.07
    Activations Density 0.013%

    No Known Activations