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. 22-LLAMASCOPE-RES-131K
    6. 4807
    Prev
    Next
    INDEX
    Explanations

    instances of the word "form" in various contexts related to creation or establishment

    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
    зм
    -0.08
    ender
    -0.07
    .boost
    -0.07
    _inches
    -0.07
    ãĥĻãĥ«
    -0.07
    _Items
    -0.07
    reed
    -0.07
    boo
    -0.07
    976
    -0.07
    eland
    -0.07
    POSITIVE LOGITS
     bonds
    0.10
    ulating
    0.10
     partnerships
    0.09
     friendships
    0.09
     alliances
    0.09
    -formed
    0.08
     bond
    0.08
    ulates
    0.08
     opinions
    0.08
     into
    0.08
    Activations Density 0.018%

    No Known Activations