© 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. 124316
    Prev
    Next
    INDEX
    Explanations

    expressions indicating personal anecdotes or experiences

    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
    ogan
    -0.09
    oku
    -0.08
    ntag
    -0.07
    rea
    -0.07
    276
    -0.07
    reas
    -0.07
     bef
    -0.07
    deaux
    -0.06
    aises
    -0.06
    onta
    -0.06
    POSITIVE LOGITS
    sol
    0.07
     note
    0.06
     simple
    0.06
    metis
    0.06
    iyas
    0.06
    simple
    0.06
    ITT
    0.06
    omen
    0.06
     ct
    0.05
    echan
    0.05
    Activations Density 0.009%

    No Known Activations