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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5348
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences of being bullied

    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
    iddi
    -0.08
    çĭĤ
    -0.07
    ekim
    -0.07
    STRUCTOR
    -0.07
    .googleapis
    -0.07
    ordo
    -0.07
    infinity
    -0.07
     Teens
    -0.07
    morgan
    -0.07
    à¹Īà¸Ńà¹Ħà¸Ľ
    -0.07
    POSITIVE LOGITS
     bullying
    0.12
     bullied
    0.10
     bully
    0.10
     recess
    0.10
     classmates
    0.10
     bull
    0.09
     lunch
    0.09
     playground
    0.09
     class
    0.09
     popularity
    0.09
    Activations Density 0.044%

    No Known Activations