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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 71197
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving goals and obtaining things

    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
    jar
    -0.07
    onis
    -0.07
     tar
    -0.06
    acht
    -0.06
    ja
    -0.06
    eda
    -0.06
    vla
    -0.06
    /doc
    -0.06
    STITUTE
    -0.06
    .promise
    -0.06
    POSITIVE LOGITS
     Weber
    0.07
    ape
    0.06
    /Web
    0.06
    _WRAPPER
    0.06
    villa
    0.06
    ÑĤен
    0.06
    lán
    0.06
    UFFIX
    0.06
    еÑĢед
    0.06
    wow
    0.06
    Activations Density 0.026%

    No Known Activations