© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82772
    Prev
    Next
    INDEX
    Explanations

    incidents of physical injury or accidents

    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
    FRING
    -0.06
    fresh
    -0.06
    æijĩ
    -0.06
    çIJĥ
    -0.06
    aths
    -0.06
    bian
    -0.06
    agar
    -0.06
    sts
    -0.06
    erate
    -0.06
    ago
    -0.06
    POSITIVE LOGITS
    stamp
    0.07
     hã
    0.07
    losed
    0.07
    .oracle
    0.06
    HEMA
    0.06
    Stamp
    0.06
    ì°©
    0.06
     unb
    0.06
    vfs
    0.06
    eted
    0.06
    Activations Density 0.005%

    No Known Activations