© 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. 28934
    Prev
    Next
    INDEX
    Explanations

    references to the United States' relationships and assistance to Madagascar

    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
    оÑģп
    -0.07
    LookAndFeel
    -0.06
    ³
    -0.06
    ¶Į
    -0.06
    amework
    -0.06
    AGER
    -0.06
    memberof
    -0.06
    defs
    -0.06
    olls
    -0.06
    .nlm
    -0.06
    POSITIVE LOGITS
    inate
    0.07
    sville
    0.07
    atern
    0.06
     pimp
    0.06
    ffffffff
    0.06
    íĪ¬
    0.06
    è£
    0.06
    arness
    0.06
    omid
    0.06
    Ī
    0.06
    Activations Density 0.005%

    No Known Activations