© 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. 87175
    Prev
    Next
    INDEX
    Explanations

    details related to proximity and location

    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
    .animations
    -0.07
    íĪ¬
    -0.07
    verty
    -0.07
    <decltype
    -0.07
    èĩªæ²»
    -0.06
    ilos
    -0.06
    asa
    -0.06
     æ°ij
    -0.06
    atori
    -0.06
    EventManager
    -0.06
    POSITIVE LOGITS
    aging
    0.06
     further
    0.06
    663
    0.06
    heid
    0.06
    spo
    0.06
    lü
    0.06
    acyj
    0.06
    amen
    0.06
    achsen
    0.06
    oc
    0.06
    Activations Density 0.004%

    No Known Activations