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. 44131
    Prev
    Next
    INDEX
    Explanations

    symbols related to technical or mathematical notation

    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
    éĥİ
    -0.07
    enko
    -0.07
    ãĥ¬ãĥ³
    -0.07
    914
    -0.06
    dik
    -0.06
     Blanco
    -0.06
    ãĥ¬ãĥ¼
    -0.06
     DEFINE
    -0.06
    FK
    -0.06
    ī
    -0.06
    POSITIVE LOGITS
     OW
    0.10
     Milwaukee
    0.09
     Manit
    0.09
     UW
    0.09
     Wisconsin
    0.09
     Fond
    0.09
     repe
    0.08
     Party
    0.08
     party
    0.07
     Wis
    0.07
    Activations Density 0.004%

    No Known Activations