© 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. 15-LLAMASCOPE-RES-131K
    11. 89608
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or states of being, particularly those that involve the verb "to be" and its various forms

    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
    oci
    -0.06
     дело
    -0.06
    èĬĤ
    -0.06
    ymph
    -0.06
    ç¯Ģ
    -0.06
    /to
    -0.06
    /dr
    -0.06
    TRL
    -0.06
    oin
    -0.06
    el
    -0.06
    POSITIVE LOGITS
    ä¹İ
    0.07
    ithe
    0.07
    ebb
    0.07
    iveness
    0.07
    aleigh
    0.07
    umas
    0.07
    ÙĦاÙħ
    0.07
    idente
    0.07
    ebo
    0.07
    atham
    0.06
    Activations Density 0.007%

    No Known Activations