© 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. 54549
    Prev
    Next
    INDEX
    Explanations

    phrases related to research proposals and methodologies

    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
    ugu
    -0.07
    ìłľ
    -0.07
     exerc
    -0.07
    rve
    -0.07
    _refl
    -0.07
    amedi
    -0.07
     Obr
    -0.07
    rst
    -0.06
    cela
    -0.06
    abeth
    -0.06
    POSITIVE LOGITS
    bserv
    0.06
    .vs
    0.06
    stown
    0.06
    ableObject
    0.06
    InThe
    0.06
     partially
    0.06
    inkel
    0.06
    пÑĢиклад
    0.06
     [](
    0.06
    izm
    0.06
    Activations Density 0.000%

    No Known Activations