© 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. 5-LLAMASCOPE-RES-131K
    6. 126837
    Prev
    Next
    INDEX
    Explanations

    descriptions of flat landscapes

    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
     Coll
    -0.07
    arga
    -0.07
    /umd
    -0.07
    MUX
    -0.07
     Grip
    -0.07
    abra
    -0.07
    GRID
    -0.07
    -INF
    -0.07
    ож
    -0.06
    iked
    -0.06
    POSITIVE LOGITS
    atic
    0.07
     BBB
    0.06
     hor
    0.06
    oking
    0.06
    ilenames
    0.06
     rabbits
    0.06
    vens
    0.05
    ¼
    0.05
     ê
    0.05
    TT
    0.05
    Activations Density 0.009%

    No Known Activations