© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 55765
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "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
    arella
    -0.07
    antz
    -0.07
     Loving
    -0.06
    енÑı
    -0.06
    (íģ¬ê¸°
    -0.06
    jabi
    -0.06
    IGO
    -0.06
    hlas
    -0.06
    ENCE
    -0.06
    lyph
    -0.06
    POSITIVE LOGITS
    zag
    0.07
    éĽ
    0.07
    owo
    0.06
    SystemService
    0.06
    WL
    0.06
    qw
    0.06
     ew
    0.06
    chk
    0.06
    ewis
    0.06
    AdapterFactory
    0.06
    Activations Density 0.065%

    No Known Activations