© 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. 123988
    Prev
    Next
    INDEX
    Explanations

    actions and movements leading to concealment or disappearance

    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
     Stub
    -0.07
    iren
    -0.07
    .Modified
    -0.06
    _ENDIAN
    -0.06
    _sphere
    -0.06
     screaming
    -0.06
    اÙĨس
    -0.06
     eps
    -0.06
     EPS
    -0.06
     subclass
    -0.06
    POSITIVE LOGITS
     behind
    0.15
     hiding
    0.12
     Behind
    0.12
     hides
    0.12
     hide
    0.12
    Behind
    0.11
     hid
    0.11
    -hide
    0.10
    beh
    0.10
    èĹı
    0.10
    Activations Density 0.044%

    No Known Activations