© 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 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. 118765
    Prev
    Next
    INDEX
    Explanations

    phrases related to approval and objection

    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
    ูà¸Ĭ
    -0.08
    ermal
    -0.07
    TargetException
    -0.07
    vÃŃm
    -0.07
    andas
    -0.07
    PLE
    -0.07
     humili
    -0.07
    üç
    -0.07
    оваÑħ
    -0.07
     Tits
    -0.07
    POSITIVE LOGITS
     objection
    0.10
     objections
    0.10
     object
    0.09
     Objects
    0.09
    obj
    0.09
    Obj
    0.08
     obj
    0.08
    Object
    0.08
     objects
    0.08
     Object
    0.08
    Activations Density 0.054%

    No Known Activations