© 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. 105011
    Prev
    Next
    INDEX
    Explanations

    references to music albums and their significance

    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
    odore
    -0.07
    iginal
    -0.07
    rices
    -0.07
    ocz
    -0.07
    orida
    -0.07
    rance
    -0.07
     Twitch
    -0.06
    ighton
    -0.06
    487
    -0.06
     γεÏģ
    -0.06
    POSITIVE LOGITS
     Dublin
    0.12
     Belfast
    0.11
     Irish
    0.10
     Ireland
    0.09
     Conor
    0.08
     Guinness
    0.07
     RTE
    0.07
    éĤ¦
    0.07
     Celtic
    0.07
    λλι
    0.07
    Activations Density 0.008%

    No Known Activations