© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 107181
    Prev
    Next
    INDEX
    Explanations

    mentions of parameters in various contexts

    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
    iw
    -0.09
    .scalablytyped
    -0.09
    PointerException
    -0.08
    haar
    -0.08
    edor
    -0.08
    ultz
    -0.07
    edList
    -0.07
    วรร
    -0.07
    ãĥ¡ãĥ³ãĥĪ
    -0.07
    iktig
    -0.07
    POSITIVE LOGITS
    urt
    0.07
    ot
    0.06
    ut
    0.06
    ä¹Ī
    0.06
    etrize
    0.06
    ìłĪ
    0.06
    Ìģ
    0.06
    par
    0.06
    agnetic
    0.06
    ãĥ¼
    0.06
    Activations Density 0.005%

    No Known Activations