© 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. 31347
    Prev
    Next
    INDEX
    Explanations

    specific mentions of official titles, roles, and statuses

    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
    ampo
    -0.07
    ypo
    -0.07
    ây
    -0.07
    azes
    -0.07
    andest
    -0.07
    (super
    -0.07
    appa
    -0.07
    .Butter
    -0.07
    iores
    -0.07
    à¹Ħà¸ĭà¸ķ
    -0.07
    POSITIVE LOGITS
     following
    0.07
     provisions
    0.07
    asan
    0.06
     shall
    0.06
     duration
    0.06
    ismus
    0.06
    ka
    0.06
    xic
    0.06
     amount
    0.06
    UBLE
    0.06
    Activations Density 0.012%

    No Known Activations