© 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. 126795
    Prev
    Next
    INDEX
    Explanations

    programming concepts and structures

    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
    تر
    -0.07
     nackte
    -0.07
    ÑģÑĮого
    -0.06
    оÑħ
    -0.06
    atik
    -0.06
    inherits
    -0.06
    kuk
    -0.06
    ibel
    -0.06
    erk
    -0.06
    claimer
    -0.06
    POSITIVE LOGITS
    ENTA
    0.08
    éĴ®
    0.08
    ãĥīãĥ«
    0.07
    .scalablytyped
    0.07
    uled
    0.07
    PERT
    0.07
    %%%%%%%%
    0.07
    :frame
    0.06
    venes
    0.06
     singly
    0.06
    Activations Density 0.014%

    No Known Activations