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

    Neuronpedia

    APICircuit 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. 5471
    Prev
    Next
    INDEX
    Explanations

    instances of discrimination or lack of awareness regarding critical social 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
    allel
    -0.08
    pone
    -0.07
    rof
    -0.07
    asket
    -0.07
    uae
    -0.07
    allet
    -0.07
    ìłĿ
    -0.07
     appDelegate
    -0.07
     Dover
    -0.07
    .firebaseapp
    -0.06
    POSITIVE LOGITS
     rein
    0.06
    FF
    0.06
    Transparent
    0.06
     democr
    0.06
     impunity
    0.06
     transparent
    0.06
    ded
    0.06
    SH
    0.05
     decent
    0.05
     public
    0.05
    Activations Density 0.000%

    No Known Activations