© 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. 58005
    Prev
    Next
    INDEX
    Explanations

    references to technical or programming aspects

    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
    uckles
    -0.06
    ãĥ¼ãĤ¹
    -0.06
    žit
    -0.06
    spiel
    -0.06
    wards
    -0.06
    ará
    -0.06
     Fle
    -0.06
    lich
    -0.06
    hotmail
    -0.05
    isbury
    -0.05
    POSITIVE LOGITS
    iol
    0.07
    oki
    0.07
    abb
    0.07
    åľ
    0.06
    erez
    0.06
    antas
    0.06
    hk
    0.06
    Mappings
    0.06
    è¶ħ
    0.06
    "struct
    0.06
    Activations Density 0.000%

    No Known Activations