Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29247
    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
    nof
    -0.07
    ooke
    -0.07
    844
    -0.06
    766
    -0.06
    utton
    -0.06
     пом
    -0.06
    ohen
    -0.06
    vore
    -0.06
    nob
    -0.06
    anton
    -0.05
    POSITIVE LOGITS
    uyá»ĩt
    0.06
    ((((
    0.06
    zial
    0.06
    avern
    0.06
     колÑĮ
    0.06
    ovenant
    0.06
    ìĬ´
    0.06
     Frost
    0.06
    ifax
    0.06
     LoginActivity
    0.06
    Activations Density 0.003%

    No Known Activations