© 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. 84070
    Prev
    Next
    INDEX
    Explanations

    mentions of "the" in varying contexts, particularly emphasizing situations involving crises or conflict

    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
    RAINT
    -0.08
    аниÑĨ
    -0.08
    marshaller
    -0.08
    TRL
    -0.08
    cház
    -0.08
    ekler
    -0.08
     omas
    -0.07
    jang
    -0.07
    ecast
    -0.07
    atre
    -0.07
    POSITIVE LOGITS
    iv
    0.06
     now
    0.05
    çļĦäºĭ
    0.05
    uming
    0.05
     strangers
    0.05
     Corp
    0.05
    acist
    0.05
     Fade
    0.05
    uling
    0.05
    æĽ¼
    0.05
    Activations Density 0.058%

    No Known Activations