© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126027
    Prev
    Next
    INDEX
    Explanations

    terms related to time and change

    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
     ens
    -0.06
    umper
    -0.06
    721
    -0.06
    ing
    -0.06
    _masks
    -0.06
    /from
    -0.06
    onom
    -0.05
    dbc
    -0.05
     bastard
    -0.05
    /UI
    -0.05
    POSITIVE LOGITS
    ugin
    0.08
     Locker
    0.07
    anan
    0.07
     FactoryBot
    0.07
    strom
    0.07
    าà¸į
    0.07
    UGIN
    0.07
    .Binding
    0.07
    iew
    0.06
    OMPI
    0.06
    Activations Density 0.001%

    No Known Activations