© 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. 56287
    Prev
    Next
    INDEX
    Explanations

    terms related to financial exploitation and guardianship issues

    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
    .dk
    -0.07
    edla
    -0.07
    èŃī
    -0.06
    秣
    -0.06
    orsi
    -0.06
     ÐĹаÑħ
    -0.06
    -grade
    -0.06
    amas
    -0.06
    ADR
    -0.06
    æĨ¶
    -0.06
    POSITIVE LOGITS
    mort
    0.06
    vil
    0.06
     Prod
    0.06
     æ»
    0.06
     menj
    0.06
     Alzheimer
    0.06
     Mort
    0.06
    WithOptions
    0.06
    gre
    0.06
    ÐĴС
    0.06
    Activations Density 0.000%

    No Known Activations