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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95632
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual or organization associated with activities and events

    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
    ialog
    -0.07
     Vin
    -0.06
    adero
    -0.06
     Neutral
    -0.06
    riad
    -0.06
    loys
    -0.06
    gem
    -0.06
    \Active
    -0.06
    ster
    -0.06
     member
    -0.06
    POSITIVE LOGITS
    éĻ£
    0.07
    HONE
    0.07
    :normal
    0.07
    ede
    0.06
    snap
    0.06
    (es
    0.06
    ules
    0.06
    s
    0.06
    /backend
    0.06
    _singular
    0.06
    Activations Density 0.001%

    No Known Activations