© 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. 129174
    Prev
    Next
    INDEX
    Explanations

    references to scientific research and educational resources

    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
     status
    -0.06
     reserved
    -0.06
     Thesis
    -0.06
     Wisdom
    -0.05
     Status
    -0.05
     de
    -0.05
     not
    -0.05
     Maid
    -0.05
    riors
    -0.05
    addError
    -0.05
    POSITIVE LOGITS
    kit
    0.08
    oki
    0.08
    erli
    0.08
     ResourceType
    0.08
    kits
    0.07
    è°
    0.07
    ÑģÑĤÑİ
    0.07
    flate
    0.07
    æĿIJæĸĻ
    0.07
    okie
    0.07
    Activations Density 0.028%

    No Known Activations