© 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. 28803
    Prev
    Next
    INDEX
    Explanations

    contrasts and conflicting ideas

    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
    ãĥ¼ãĥĢ
    -0.06
    ail
    -0.06
    ishi
    -0.06
    ola
    -0.06
     godt
    -0.06
    idar
    -0.06
    uzz
    -0.06
    AIL
    -0.06
    itung
    -0.06
    quila
    -0.06
    POSITIVE LOGITS
     always
    0.16
    always
    0.14
     Always
    0.13
     overall
    0.12
    Always
    0.12
     ALWAYS
    0.11
     toujours
    0.11
     sempre
    0.11
     altogether
    0.11
    overall
    0.11
    Activations Density 0.107%

    No Known Activations