© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75373
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    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
    ilon
    -0.06
    rait
    -0.06
    lege
    -0.06
    ecast
    -0.06
    iday
    -0.06
    discard
    -0.06
     Magnet
    -0.06
     Rein
    -0.06
    uncture
    -0.06
    udence
    -0.06
    POSITIVE LOGITS
    άνÏĦα
    0.07
    ayah
    0.06
    izm
    0.06
    ÑĢоз
    0.06
    addir
    0.06
     Mahar
    0.06
    ÏĦÏģ
    0.06
    vron
    0.06
    369
    0.06
    .eth
    0.06
    Activations Density 0.000%

    No Known Activations