© 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. 71907
    Prev
    Next
    INDEX
    Explanations

    occurrences of names and collaborations

    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
    tres
    -0.07
    )((((
    -0.07
    å±ĭ
    -0.07
    wg
    -0.07
    зи
    -0.07
     ráno
    -0.07
    dw
    -0.07
    иж
    -0.07
    åħ¸
    -0.06
    див
    -0.06
    POSITIVE LOGITS
    amp
    0.12
     co
    0.11
    AMP
    0.09
     amp
    0.09
     partner
    0.08
     accomp
    0.08
    quot
    0.07
     associates
    0.07
     Partners
    0.07
     Associates
    0.07
    Activations Density 0.090%

    No Known Activations