© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94269
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consideration or opinion about a subject

    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
    opic
    -0.07
    isor
    -0.07
    opsis
    -0.06
    ýš
    -0.06
    dera
    -0.06
    ÑĢÑİ
    -0.06
    ısından
    -0.06
    802
    -0.06
     regain
    -0.06
    IEWS
    -0.06
    POSITIVE LOGITS
     Sesso
    0.07
    ëŀĺ
    0.06
    Setter
    0.06
    icina
    0.06
    EMPLARY
    0.06
    _DIRECTION
    0.06
    ioni
    0.06
     Beard
    0.06
    zdy
    0.06
     haf
    0.06
    Activations Density 0.000%

    No Known Activations