© 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. 9-LLAMASCOPE-RES-131K
    11. 96817
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "with" 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
    ãģŁãģĹ
    -0.07
    -ser
    -0.06
    ,LOCATION
    -0.06
    Ïģε
    -0.06
    ÑijÑĤ
    -0.06
     ser
    -0.05
    staking
    -0.05
    廳
    -0.05
     apparent
    -0.05
    ül
    -0.05
    POSITIVE LOGITS
    quate
    0.07
    atham
    0.07
    mate
    0.07
    BOTTOM
    0.06
    -carousel
    0.06
    obo
    0.06
    ë²Ķ
    0.06
    stral
    0.06
    rix
    0.06
     ~>
    0.06
    Activations Density 0.000%

    No Known Activations