© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3276
    Prev
    Next
    INDEX
    Explanations

    numerical data related to scientific measurements or codes

    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
    =view
    -0.06
     razor
    -0.06
    144
    -0.06
    ester
    -0.06
    éϰ
    -0.06
    alez
    -0.06
    olini
    -0.06
    201
    -0.05
    attle
    -0.05
    ioni
    -0.05
    POSITIVE LOGITS
    ÎĨ
    0.07
     Amph
    0.07
     shemale
    0.07
    elman
    0.07
    PIC
    0.07
    VED
    0.07
    resher
    0.07
    ugins
    0.07
     ÙĨØ®
    0.07
    kili
    0.07
    Activations Density 0.007%

    No Known Activations