© 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. 41658
    Prev
    Next
    INDEX
    Explanations

    words expressing positivity or strength in various contexts

    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
    ChangeEvent
    -0.07
    иÑĤоÑĢ
    -0.07
    unto
    -0.07
    ÐļТ
    -0.06
    abez
    -0.06
    ail
    -0.06
    mez
    -0.06
    incinn
    -0.06
    ellite
    -0.06
    åŁ
    -0.06
    POSITIVE LOGITS
     view
    0.07
     grasp
    0.07
     chance
    0.06
     impact
    0.06
    VERTISE
    0.06
     sense
    0.06
    åĻ¨
    0.06
     role
    0.06
    ennon
    0.06
     understanding
    0.06
    Activations Density 0.045%

    No Known Activations