© 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. 107302
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and related attributes or descriptors

    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
     itself
    -0.14
     themselves
    -0.11
     its
    -0.08
     their
    -0.08
     
    -0.07
    leur
    -0.07
     Its
    -0.06
    their
    -0.06
     collective
    -0.06
    at
    -0.06
    POSITIVE LOGITS
     himself
    0.12
    /her
    0.11
    /she
    0.11
    arken
    0.08
    inous
    0.08
    fty
    0.08
    radan
    0.08
    panic
    0.08
    ses
    0.08
    his
    0.07
    Activations Density 0.282%

    No Known Activations