Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96226
    Prev
    Next
    INDEX
    Explanations

    terms related to armed forces and military actions

    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
    gether
    -0.09
    ãĥ£
    -0.08
    onis
    -0.08
    ÌĨ
    -0.08
    odore
    -0.08
    istrovstvÃŃ
    -0.08
    urnal
    -0.07
    zers
    -0.07
    .wp
    -0.07
    tle
    -0.07
    POSITIVE LOGITS
    .$.
    0.07
    olut
    0.07
    .sigma
    0.06
    ê¸°ë¡ľ
    0.06
    ศาสà¸ķร
    0.06
    uff
    0.06
    ned
    0.06
    YW
    0.06
    baÅŁ
    0.06
    elter
    0.06
    Activations Density 0.007%

    No Known Activations