© 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. 85575
    Prev
    Next
    INDEX
    Explanations

    punctuation marks 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
    omik
    -0.08
    á»Ńa
    -0.07
    ooter
    -0.07
    ainen
    -0.07
     Epoch
    -0.07
    ìłĪ
    -0.06
    illac
    -0.06
    ëħ
    -0.06
    aneously
    -0.06
    ombo
    -0.06
    POSITIVE LOGITS
     deck
    0.06
    assium
    0.06
    owell
    0.06
    arf
    0.06
    gp
    0.06
     Dav
    0.05
     Hue
    0.05
    \Bridge
    0.05
    deck
    0.05
     impression
    0.05
    Activations Density 0.000%

    No Known Activations