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. 43672
    Prev
    Next
    INDEX
    Explanations

    CSS properties and styles related to text formatting

    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
     trans
    -0.06
    plete
    -0.06
     Peters
    -0.06
    rij
    -0.05
     Gard
    -0.05
    etr
    -0.05
    ...↵
    -0.05
    thumbnail
    -0.05
    trans
    -0.05
    POSITIVE LOGITS
    $MESS
    0.09
    .keyword
    0.08
     keyword
    0.08
    ninger
    0.08
    _keywords
    0.08
    _fore
    0.07
    _keyword
    0.07
     RESERVED
    0.07
    keyword
    0.07
     folding
    0.07
    Activations Density 0.007%

    No Known Activations