© 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. 116962
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of providing or offering something

    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
     Ta
    -0.06
    ypo
    -0.06
     кал
    -0.06
    ÑĦик
    -0.06
    irst
    -0.06
     život
    -0.05
    osy
    -0.05
     anth
    -0.05
    sworth
    -0.05
     ky
    -0.05
    POSITIVE LOGITS
    .blob
    0.07
    _UC
    0.07
    illet
    0.07
    ujete
    0.07
    icamente
    0.07
    getManager
    0.07
    ανά
    0.07
    ilit
    0.07
    abler
    0.07
     pod
    0.07
    Activations Density 0.010%

    No Known Activations