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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 107052
    Prev
    Next
    INDEX
    Explanations

    references to estates or state-related concepts

    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
    addin
    -0.07
    reesome
    -0.07
    mast
    -0.07
    rita
    -0.07
    rieg
    -0.07
    ahir
    -0.07
    ãĥĨãĥ«
    -0.07
    оÑĹ
    -0.07
    thes
    -0.06
     Habitat
    -0.06
    POSITIVE LOGITS
    ois
    0.09
    -wide
    0.09
    wide
    0.08
    uffix
    0.07
    builder
    0.07
    ified
    0.07
    mate
    0.07
    elijke
    0.07
    udy
    0.07
    uary
    0.07
    Activations Density 0.005%

    No Known Activations