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. 95983
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Bookmark."

    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
    ,
    -0.06
    ouch
    -0.05
    ape
    -0.05
     an
    -0.05
    zk
    -0.05
     Pearson
    -0.05
     Hoch
    -0.05
    ↵
    -0.05
     (
    -0.05
    ched
    -0.05
    POSITIVE LOGITS
    -uri
    0.08
    éijij
    0.08
    .Focused
    0.08
    è³¢
    0.07
    uckle
    0.07
    VERR
    0.07
    StreamReader
    0.07
    íĥľ
    0.07
    .readyState
    0.07
     informacÃŃ
    0.07
    Activations Density 0.001%

    No Known Activations