© 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. 9-LLAMASCOPE-RES-131K
    11. 98381
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pitch" and related terms in the context of proposals or ideas

    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
    liness
    -0.09
    Ìĥ
    -0.08
    nd
    -0.07
    -fashioned
    -0.07
    ely
    -0.07
    -thirds
    -0.07
    athan
    -0.06
    bject
    -0.06
    vit
    -0.06
    ders
    -0.06
    POSITIVE LOGITS
    fork
    0.13
    ering
    0.07
    ãĤĤãģĹ
    0.07
    phrase
    0.07
    rganization
    0.07
    ìĻĦ
    0.07
    bilt
    0.07
    weak
    0.07
    punkt
    0.07
    grounds
    0.07
    Activations Density 0.011%

    No Known Activations