© 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. 55833
    Prev
    Next
    INDEX
    Explanations

    mentions of account creation and membership-related concepts

    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
    erg
    -0.06
     Vi
    -0.06
    achten
    -0.06
    iene
    -0.06
    isku
    -0.06
    ilim
    -0.06
    charset
    -0.06
    List
    -0.06
    pon
    -0.06
    ij¸
    -0.06
    POSITIVE LOGITS
    /sign
    0.07
     crossorigin
    0.07
    AndGet
    0.07
    NCY
    0.07
    /***/
    0.07
     free
    0.06
    åħįè´¹
    0.06
    required
    0.06
    mise
    0.06
     requ
    0.06
    Activations Density 0.022%

    No Known Activations