© 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. 106957
    Prev
    Next
    INDEX
    Explanations

    phrases related to copyright and content use rights

    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
    ifies
    -0.07
     Sect
    -0.06
    िà¤ķल
    -0.06
     пÑĢавда
    -0.06
    izio
    -0.06
     воÑĤ
    -0.06
    á»±
    -0.06
    issan
    -0.06
    تد
    -0.06
    nos
    -0.06
    POSITIVE LOGITS
     content
    0.10
     copyrighted
    0.08
    åĨħ容
    0.07
     getContent
    0.07
    ambi
    0.07
     ActiveForm
    0.07
     portions
    0.07
    ifetime
    0.07
    aleur
    0.07
    ngrx
    0.07
    Activations Density 0.012%

    No Known Activations