© 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. 22-LLAMASCOPE-RES-131K
    11. 4222
    Prev
    Next
    INDEX
    Explanations

    names or references to specific individuals, particularly politicians

    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
    ombine
    -0.08
    bestos
    -0.08
    avings
    -0.08
    vailability
    -0.08
    reur
    -0.08
    htar
    -0.08
    elage
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    สà¸Ńà¸ļ
    -0.07
    erap
    -0.07
    POSITIVE LOGITS
    ãĥ§
    0.06
    uento
    0.06
    izz
    0.06
    ourt
    0.06
    is
    0.06
    iqu
    0.06
    ig
    0.05
    WP
    0.05
    WND
    0.05
    ic
    0.05
    Activations Density 0.002%

    No Known Activations