© 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. 42173
    Prev
    Next
    INDEX
    Explanations

    references to specific musical pieces or compositions

    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
    ↵
    -0.07
     resent
    -0.06
     ##
    -0.06
     -
    -0.06
     sm
    -0.06
     m
    -0.06
    _
    -0.06
     e
    -0.05
    iese
    -0.05
     n
    -0.05
    POSITIVE LOGITS
    ãĤ¾
    0.09
    mamak
    0.09
    GINE
    0.08
    STYPE
    0.08
    _Zero
    0.08
    ì£
    0.08
    ?url
    0.08
    avr
    0.08
    ZERO
    0.08
    ÑĤаж
    0.08
    Activations Density 0.024%

    No Known Activations