© 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. 117820
    Prev
    Next
    INDEX
    Explanations

    verbs indicating statements or expressions of opinion

    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
     himself
    -0.10
     Himself
    -0.07
     herself
    -0.06
    ulf
    -0.06
     Inhal
    -0.06
    ìĿij
    -0.06
    Pros
    -0.06
     seinem
    -0.06
     unto
    -0.06
    èĹı
    -0.06
    POSITIVE LOGITS
     itself
    0.10
     its
    0.08
    igu
    0.08
    ocale
    0.08
     Its
    0.07
    ozy
    0.07
    Its
    0.07
    ziej
    0.07
    rita
    0.07
    .gms
    0.07
    Activations Density 0.006%

    No Known Activations