© 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. 106873
    Prev
    Next
    INDEX
    Explanations

    instances of persuasion and attempts to convince someone

    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
    RelativeTo
    -0.08
    òi
    -0.08
    æ¢
    -0.08
    esis
    -0.08
     Verfüg
    -0.07
    ìĵ°
    -0.07
    åķª
    -0.07
    ãģ¾ãģļ
    -0.07
     DISCLAIM
    -0.07
     mev
    -0.07
    POSITIVE LOGITS
     yesterday
    0.07
     tonight
    0.06
    allo
    0.06
     mud
    0.06
     today
    0.06
     controls
    0.06
     altogether
    0.06
     tomorrow
    0.06
     reconc
    0.05
    .↵
    0.05
    Activations Density 0.044%

    No Known Activations