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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73536
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate perception or conjecture regarding actions or states

    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
    illions
    -0.07
     supposedly
    -0.07
    appen
    -0.07
    pond
    -0.06
    ammable
    -0.06
    immer
    -0.06
     reputed
    -0.06
    ayas
    -0.06
    .u
    -0.06
    ạp
    -0.06
    POSITIVE LOGITS
     Bun
    0.06
    inger
    0.06
     nowhere
    0.06
    opal
    0.06
     attempt
    0.06
     terra
    0.06
    SETS
    0.06
    Favorites
    0.06
    umu
    0.06
    INGER
    0.06
    Activations Density 0.013%

    No Known Activations