Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76500
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "be" in various forms and contexts

    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
    à¹į
    -0.06
     LENG
    -0.06
     Hlav
    -0.06
    ITO
    -0.06
    COLUMN
    -0.06
    velt
    -0.06
     Epoch
    -0.06
    _DEFINED
    -0.06
    çĭ
    -0.06
    fieldname
    -0.06
    POSITIVE LOGITS
    arrow
    0.06
    abin
    0.06
     cater
    0.06
    accom
    0.06
     seedu
    0.06
    ignon
    0.06
     judicial
    0.06
    ime
    0.06
    _locals
    0.06
     apparent
    0.06
    Activations Density 0.086%

    No Known Activations