© 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. 72028
    Prev
    Next
    INDEX
    Explanations

    expressions questioning quantity or degree

    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
     often
    -0.07
     frequently
    -0.06
     ink
    -0.06
    visor
    -0.06
    rn
    -0.06
    ent
    -0.06
     immediately
    -0.05
    som
    -0.05
     nowhere
    -0.05
    acle
    -0.05
    POSITIVE LOGITS
    TargetException
    0.08
    deaux
    0.07
    upe
    0.07
    ulton
    0.07
    sı
    0.07
    ellij
    0.07
    ĥn
    0.07
    ãģŀ
    0.07
     tol
    0.07
    ULATE
    0.07
    Activations Density 0.014%

    No Known Activations