© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126768
    Prev
    Next
    INDEX
    Explanations

    references to physical endurance and challenges

    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
    ziej
    -0.07
    hoa
    -0.07
    oyo
    -0.07
    .neo
    -0.07
     extradition
    -0.07
    iego
    -0.07
    agner
    -0.07
    ême
    -0.06
    dam
    -0.06
    ERA
    -0.06
    POSITIVE LOGITS
     trainers
    0.08
     fitness
    0.07
     training
    0.07
    /boot
    0.07
     Fitness
    0.07
    priv
    0.07
     priv
    0.07
     éĥ¨
    0.06
    çĶ
    0.06
     privilege
    0.06
    Activations Density 0.029%

    No Known Activations