© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 71118
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to individuals

    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
    adelphia
    -0.09
    .tie
    -0.08
    heim
    -0.08
    theid
    -0.08
    ød
    -0.08
    quisitions
    -0.07
    iasm
    -0.07
    ajas
    -0.07
    çak
    -0.07
    ylland
    -0.07
    POSITIVE LOGITS
     band
    0.06
     Christmas
    0.06
     exclus
    0.06
     act
    0.06
     Lux
    0.05
     tracks
    0.05
     Ministry
    0.05
    MC
    0.05
     phenomenon
    0.05
    ÃŃÅĻ
    0.05
    Activations Density 0.003%

    No Known Activations