© 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. 107347
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "was" and its conjugations indicating past actions or states

    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
    149
    -0.08
    eldorf
    -0.06
    386
    -0.06
    ères
    -0.06
    jure
    -0.06
    кÑĢаÑĹ
    -0.06
    à¥Įà¤ķ
    -0.06
    quisite
    -0.06
     Stereo
    -0.06
    apl
    -0.06
    POSITIVE LOGITS
    -Cal
    0.06
    sure
    0.06
    íĹĮ
    0.06
    rts
    0.06
    bach
    0.06
    gett
    0.06
    åĨł
    0.06
    Bomb
    0.06
     ÙĦØŃ
    0.05
    ãĥ¼ãĥĦ
    0.05
    Activations Density 0.042%

    No Known Activations