© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61301
    Prev
    Next
    INDEX
    Explanations

    instances of the word "me" and related pronouns in various contexts

    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
    e
    -0.07
    vsp
    -0.06
    omez
    -0.06
    dra
    -0.06
     itself
    -0.06
    ickerView
    -0.06
    iphy
    -0.06
     denen
    -0.06
    jun
    -0.06
    _FALL
    -0.06
    POSITIVE LOGITS
    /us
    0.07
    chema
    0.07
    pected
    0.07
    hec
    0.06
    ảo
    0.06
    auc
    0.06
     baise
    0.06
    ENCHMARK
    0.06
     rằng
    0.06
    kdir
    0.06
    Activations Density 0.012%

    No Known Activations