© 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. 87157
    Prev
    Next
    INDEX
    Explanations

    elements related to project titles and versioning in documentation or code

    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
     Gratuit
    -0.07
    elez
    -0.07
    ipse
    -0.06
     bridges
    -0.06
    iky
    -0.06
     cheating
    -0.06
     Kir
    -0.06
    rish
    -0.06
    interop
    -0.06
    laus
    -0.06
    POSITIVE LOGITS
    èĭ
    0.07
    ILI
    0.06
    Ñĥки
    0.06
    ëĿ¼íĶ¼
    0.06
    -toggler
    0.06
    EntityType
    0.06
    å®ħ
    0.06
     оÑģÑĤаннÑĸ
    0.06
    -badge
    0.06
    _FATAL
    0.06
    Activations Density 0.000%

    No Known Activations