© 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. 73240
    Prev
    Next
    INDEX
    Explanations

    terms related to copyright and ownership

    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
    abbr
    -0.08
    ábado
    -0.07
     sovere
    -0.07
    imson
    -0.07
     porr
    -0.07
    uga
    -0.07
    ahoma
    -0.06
    ekli
    -0.06
    ibase
    -0.06
     Erotik
    -0.06
    POSITIVE LOGITS
    иÑĪ
    0.06
    oyer
    0.06
    .md
    0.06
    lichkeit
    0.06
    baar
    0.06
    arily
    0.06
    fo
    0.06
    folios
    0.06
    isy
    0.05
     Barney
    0.05
    Activations Density 0.001%

    No Known Activations