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

    Neuronpedia

    Jacobian LensNEW
    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. 130769
    Prev
    Next
    INDEX
    Explanations

    references to custom modifications and details about specific projects or items

    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
    (çģ«
    -0.07
    -Za
    -0.07
    ÄĽ
    -0.07
    ÅĤad
    -0.07
     Hd
    -0.07
    @testable
    -0.07
    ¤
    -0.07
    çĭ¼
    -0.07
    antor
    -0.06
    luet
    -0.06
    POSITIVE LOGITS
    PEC
    0.06
     filetype
    0.06
     Patreon
    0.06
    lemn
    0.06
     unspecified
    0.06
     subtract
    0.05
    nard
    0.05
    nave
    0.05
    classed
    0.05
     cheap
    0.05
    Activations Density 0.002%

    No Known Activations