© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 130169
    Prev
    Next
    INDEX
    Explanations

    elements related to documentation or descriptions in a narrative context

    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
     unb
    -0.07
     invol
    -0.06
    quip
    -0.06
     Homo
    -0.05
    abi
    -0.05
    uo
    -0.05
    Hint
    -0.05
     unsur
    -0.05
    Is
    -0.05
     hypothetical
    -0.05
    POSITIVE LOGITS
     elsewhere
    0.10
     others
    0.08
     other
    0.08
     subsequent
    0.08
    ipse
    0.07
    upal
    0.07
    alsy
    0.07
     åħ¶ä»ĸ
    0.07
    iquer
    0.07
    365
    0.07
    Activations Density 0.039%

    No Known Activations