© 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. 88901
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-acceptance and comfort

    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
    getc
    -0.08
    alette
    -0.07
    omu
    -0.07
     ÑģкÑĢÑĭ
    -0.07
    echan
    -0.07
    adu
    -0.07
    hidden
    -0.07
    ido
    -0.07
    imoto
    -0.07
    opsis
    -0.07
    POSITIVE LOGITS
     spaces
    0.07
    SelectionMode
    0.07
     Spaces
    0.07
     proverb
    0.06
     worlds
    0.06
    141
    0.06
    spaces
    0.06
     discomfort
    0.05
    rene
    0.05
     Saf
    0.05
    Activations Density 0.030%

    No Known Activations