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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80100
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ryan."

    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
    .kwargs
    -0.07
    angep
    -0.07
    clare
    -0.07
    ipa
    -0.07
    avit
    -0.07
    inson
    -0.07
     seedu
    -0.07
    leans
    -0.07
    omm
    -0.07
    yet
    -0.06
    POSITIVE LOGITS
    air
    0.07
    ian
    0.07
    ahoo
    0.06
     heroes
    0.06
    atik
    0.06
    ä»ķ
    0.06
    ight
    0.06
    edio
    0.06
    ska
    0.06
    lan
    0.05
    Activations Density 0.006%

    No Known Activations