Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57459
    Prev
    Next
    INDEX
    Explanations

    terms related to online job opportunities and earning potential

    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
    zel
    -0.07
    ="__
    -0.07
    COPY
    -0.07
    aina
    -0.06
    á»ķ
    -0.06
    ç§ij
    -0.06
     Brennan
    -0.06
     ков
    -0.06
    astos
    -0.06
    supported
    -0.06
    POSITIVE LOGITS
     surveys
    0.07
    /tasks
    0.07
     Harris
    0.07
     participation
    0.07
     survey
    0.07
     Participation
    0.07
    antom
    0.07
     tasks
    0.07
    survey
    0.06
     Tasks
    0.06
    Activations Density 0.008%

    No Known Activations