© 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. 71420
    Prev
    Next
    INDEX
    Explanations

    HTML anchor tags and link elements

    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
    oten
    -0.08
    eten
    -0.07
    ubl
    -0.07
    ppo
    -0.06
    roat
    -0.06
     ed
    -0.06
    autoload
    -0.06
    ikal
    -0.06
     Soap
    -0.06
     card
    -0.06
    POSITIVE LOGITS
     href
    0.12
    href
    0.12
    [href
    0.10
    (href
    0.09
    .href
    0.08
    _href
    0.07
    :href
    0.07
     dest
    0.07
    Href
    0.07
     Kensington
    0.07
    Activations Density 0.010%

    No Known Activations