© 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. 15-LLAMASCOPE-RES-131K
    11. 989
    Prev
    Next
    INDEX
    Explanations

    phrases related to email communication and permission-based mailing

    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
    (?
    -0.07
    panic
    -0.06
     (?)
    -0.06
     sm
    -0.05
    olen
    -0.05
     (?
    -0.05
    rect
    -0.05
     overall
    -0.05
     simultaneous
    -0.05
    Bo
    -0.05
    POSITIVE LOGITS
    .realm
    0.08
    acos
    0.08
     desar
    0.07
    âĹıâĹı
    0.07
    /*č↵
    0.07
    Ø·ØŃ
    0.07
    ÙĪص
    0.07
    illions
    0.07
    Collapse
    0.07
    инÑĸ
    0.07
    Activations Density 0.060%

    No Known Activations