© 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. 17-LLAMASCOPE-RES-131K
    6. 16993
    Prev
    Next
    INDEX
    Explanations

    instances of usage and contribution by individuals

    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
    еÑĢж
    -0.07
    ogle
    -0.07
    lei
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    ugas
    -0.07
    elman
    -0.06
    uries
    -0.06
    ecies
    -0.06
    .scalablytyped
    -0.06
    èĤ¥
    -0.06
    POSITIVE LOGITS
    xia
    0.06
    omor
    0.06
    irk
    0.05
    iet
    0.05
     Lambert
    0.05
    ife
    0.05
     creature
    0.05
    lector
    0.05
     ---------------------------------------------------------------------------↵
    0.05
    ãĥĶãĥ¼
    0.05
    Activations Density 0.000%

    No Known Activations