© 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. 126358
    Prev
    Next
    INDEX
    Explanations

    references to human rights and fundamental entitlements

    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
    彦
    -0.07
    445
    -0.06
    struk
    -0.06
    527
    -0.06
    strict
    -0.06
    upe
    -0.06
     eins
    -0.06
    305
    -0.06
     tslint
    -0.05
    imits
    -0.05
    POSITIVE LOGITS
     rights
    0.12
     RIGHTS
    0.10
     Rights
    0.10
    -rights
    0.10
     human
    0.10
    rights
    0.09
     пÑĢава
    0.09
    -basic
    0.08
    /basic
    0.08
    Rights
    0.08
    Activations Density 0.031%

    No Known Activations