© 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. 85410
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly those indicating 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
    onga
    -0.08
    ifest
    -0.07
    ifes
    -0.06
    mith
    -0.06
    undry
    -0.06
    _oct
    -0.06
     Wend
    -0.06
     Commons
    -0.06
    utor
    -0.06
    unate
    -0.06
    POSITIVE LOGITS
     nó
    0.08
     it
    0.08
     оно
    0.07
    abr
    0.07
    å®ĥ
    0.07
    Sounds
    0.07
    floating
    0.07
    Such
    0.06
     its
    0.06
    ordum
    0.06
    Activations Density 0.057%

    No Known Activations