© 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. 71721
    Prev
    Next
    INDEX
    Explanations

    emphasis on things that are left or remaining

    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
    lis
    -0.07
    iddi
    -0.07
    jid
    -0.06
    addock
    -0.06
    [e
    -0.06
    abei
    -0.06
     Minds
    -0.06
    awa
    -0.06
    jon
    -0.06
    ilst
    -0.06
    POSITIVE LOGITS
     Adler
    0.08
    ASHBOARD
    0.07
    wards
    0.07
    -handed
    0.07
    alive
    0.07
    lander
    0.07
    <=(
    0.06
    edeki
    0.06
     Longer
    0.06
    ë°©
    0.06
    Activations Density 0.007%

    No Known Activations