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. 118708
    Prev
    Next
    INDEX
    Explanations

    uses of the first-person pronoun "I" and its associated constructions

    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
    lobber
    -0.08
    TestFixture
    -0.07
    ochen
    -0.07
    ãģªãģĮ
    -0.07
    ignum
    -0.07
    vos
    -0.06
    endale
    -0.06
    chant
    -0.06
    ichen
    -0.06
    anga
    -0.06
    POSITIVE LOGITS
     literally
    0.08
     tried
    0.07
    liter
    0.07
    .Management
    0.07
     Liter
    0.06
    jian
    0.06
     even
    0.06
    /Dk
    0.06
    omain
    0.06
    iola
    0.06
    Activations Density 0.021%

    No Known Activations