© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96308
    Prev
    Next
    INDEX
    Explanations

    nested structures in code, particularly block or object declarations

    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
    ponce
    -0.06
     Finger
    -0.06
     rem
    -0.06
    наÑĢ
    -0.06
    iesen
    -0.05
    ointment
    -0.05
    allon
    -0.05
    finger
    -0.05
    ointments
    -0.05
    .Navigator
    -0.05
    POSITIVE LOGITS
    wit
    0.08
    dent
    0.07
    iol
    0.07
    ERVE
    0.07
    ncy
    0.07
    uai
    0.07
    AREST
    0.07
    nist
    0.07
     Wet
    0.07
    olate
    0.07
    Activations Density 0.001%

    No Known Activations