© 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. 15-LLAMASCOPE-RES-131K
    6. 61914
    Prev
    Next
    INDEX
    Explanations

    pronouns that refer to individuals or groups

    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
    é¼
    -0.07
    úb
    -0.07
    icator
    -0.07
    atron
    -0.07
    aspers
    -0.07
     пеÑĢел
    -0.07
    lech
    -0.07
    afort
    -0.07
    QRS
    -0.07
    ож
    -0.07
    POSITIVE LOGITS
     imm
    0.06
    /us
    0.06
     quot
    0.06
     div
    0.06
    opp
    0.06
    om
    0.06
    omen
    0.06
     ap
    0.05
     gen
    0.05
     personally
    0.05
    Activations Density 0.058%

    No Known Activations