© 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. 107702
    Prev
    Next
    INDEX
    Explanations

    references to album-related content in a software or database context

    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
    ahoma
    -0.09
    ÙĦاÙĤ
    -0.07
    phin
    -0.07
    मत
    -0.07
    iera
    -0.07
    inces
    -0.06
    ernen
    -0.06
    \Migrations
    -0.06
    rego
    -0.06
    525
    -0.06
    POSITIVE LOGITS
     service
    0.07
    MO
    0.06
     services
    0.06
    andon
    0.06
     seeds
    0.06
    _logic
    0.06
    .ds
    0.06
    _gid
    0.06
    -tm
    0.06
    DAO
    0.06
    Activations Density 0.037%

    No Known Activations