© 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. 130136
    Prev
    Next
    INDEX
    Explanations

    references to pages or documents

    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
    ager
    -0.07
    inz
    -0.06
    AGER
    -0.05
    ENA
    -0.05
    /callback
    -0.05
    olv
    -0.05
    javax
    -0.05
    iten
    -0.05
     Abr
    -0.05
     dist
    -0.05
    POSITIVE LOGITS
    -wide
    0.08
    UnderTest
    0.08
    antry
    0.08
    oplevel
    0.07
    vangst
    0.07
    iveau
    0.07
    éĥİ
    0.07
     McCabe
    0.07
    anan
    0.07
    ÅĤad
    0.07
    Activations Density 0.008%

    No Known Activations