© 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. 17-LLAMASCOPE-RES-131K
    6. 77009
    Prev
    Next
    INDEX
    Explanations

    elements related to software styling and design attributes

    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
     att
    -0.06
    inth
    -0.06
    ability
    -0.06
    isphere
    -0.05
    10
    -0.05
     Sind
    -0.05
    abin
    -0.05
    aisy
    -0.05
     w
    -0.05
    perm
    -0.05
    POSITIVE LOGITS
    èĪŀ
    0.07
     defStyle
    0.07
    .radioButton
    0.07
    åĺī
    0.07
    allis
    0.07
    Defaults
    0.07
    chemes
    0.06
    Ðĭ
    0.06
    éŁ¿
    0.06
    herits
    0.06
    Activations Density 0.002%

    No Known Activations