© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 71724
    Prev
    Next
    INDEX
    Explanations

    words expressing interest and concern

    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
    anger
    -0.08
    sphere
    -0.07
    itchen
    -0.07
    gere
    -0.07
    meld
    -0.07
    озв
    -0.07
    angered
    -0.07
    alian
    -0.07
    arry
    -0.07
    lesai
    -0.07
    POSITIVE LOGITS
     parties
    0.09
     persons
    0.08
     individuals
    0.08
    ness
    0.08
    ieder
    0.07
    anz
    0.06
     families
    0.06
     person
    0.06
    wend
    0.06
    ences
    0.06
    Activations Density 0.003%

    No Known Activations