© 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. 75039
    Prev
    Next
    INDEX
    Explanations

    the word "such" used 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
    opoulos
    -0.08
    ensch
    -0.07
    arious
    -0.07
    ivec
    -0.07
     suche
    -0.07
    duÄŁ
    -0.07
    urf
    -0.07
    acin
    -0.07
    _RT
    -0.06
    okit
    -0.06
    POSITIVE LOGITS
    like
    0.09
    likle
    0.08
     an
    0.08
    itra
    0.07
    vez
    0.07
     a
    0.07
    ãĥ¥ãĥ¼
    0.07
     обÑĢазом
    0.07
    -sex
    0.07
    ìłĢ
    0.07
    Activations Density 0.044%

    No Known Activations