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. 43600
    Prev
    Next
    INDEX
    Explanations

    specific coded or mathematical expressions and variables

    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
    Houston
    -0.08
     Houston
    -0.08
     rodin
    -0.07
     Alabama
    -0.07
     Atlanta
    -0.07
     Detroit
    -0.07
     Irving
    -0.07
    Alabama
    -0.07
     Indianapolis
    -0.06
     Akron
    -0.06
    POSITIVE LOGITS
     Bh
    0.13
     dz
    0.11
     Dash
    0.10
     Nu
    0.10
     Ng
    0.10
     Tong
    0.09
     Zh
    0.09
     throm
    0.09
    Dash
    0.09
     lyon
    0.09
    Activations Density 0.002%

    No Known Activations