© 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. 40626
    Prev
    Next
    INDEX
    Explanations

    key terms related to challenges and systemic issues

    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
    cott
    -0.07
     Claw
    -0.06
    kou
    -0.06
    .IsAny
    -0.06
    zb
    -0.06
    ADOR
    -0.06
    ãģĶ
    -0.06
    cks
    -0.06
    yar
    -0.06
    am
    -0.06
    POSITIVE LOGITS
    antity
    0.07
    ileo
    0.07
    EventManager
    0.07
     Morrow
    0.07
    寿
    0.06
    orra
    0.06
    ornado
    0.06
    ãĥ³ãĤ¬
    0.06
    WithMany
    0.06
    <context
    0.06
    Activations Density 0.001%

    No Known Activations