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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 43898
    Prev
    Next
    INDEX
    Explanations

    sequences of characters, particularly in specific technical or mathematical contexts

    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
    DonaldTrump
    -0.08
    θε
    -0.07
    LabelText
    -0.07
    _NATIVE
    -0.07
     puta
    -0.07
    .native
    -0.07
    aab
    -0.07
    _);↵↵
    -0.07
    aoke
    -0.06
    onto
    -0.06
    POSITIVE LOGITS
    1
    0.10
     married
    0.08
    |
    0.08
     b
    0.08
    ↵
    0.07
    2
    0.07
     was
    0.07
     bapt
    0.07
    ||
    0.07
     inherited
    0.06
    Activations Density 0.003%

    No Known Activations