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. 22-LLAMASCOPE-RES-131K
    6. 5512
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Sev" and its variations

    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
    ì§Ŀ
    -0.08
    å¿ľ
    -0.07
    egot
    -0.07
    ifr
    -0.06
    ein
    -0.06
    prend
    -0.06
     å¾ĴæŃ©
    -0.06
    stein
    -0.06
    bower
    -0.06
    alus
    -0.06
    POSITIVE LOGITS
     Sev
    0.08
    кÑĥп
    0.07
    ëĭĿ
    0.07
    ente
    0.06
    orsch
    0.06
    麼
    0.06
    ORAGE
    0.06
    oya
    0.06
     ages
    0.06
     Scout
    0.06
    Activations Density 0.003%

    No Known Activations