© 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. 118826
    Prev
    Next
    INDEX
    Explanations

    instances of conditional phrases or hypothetical scenarios

    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
    erts
    -0.06
    olit
    -0.06
    dle
    -0.06
    achts
    -0.06
    acht
    -0.06
    mina
    -0.06
     Hust
    -0.06
    Å¡ov
    -0.06
    illet
    -0.06
    oldt
    -0.05
    POSITIVE LOGITS
    OKIE
    0.07
    ocz
    0.07
    ometr
    0.07
    osy
    0.06
     Cotton
    0.06
    иÑģлов
    0.06
    á»įng
    0.06
     vÃŃde
    0.06
    ahren
    0.06
     Stick
    0.06
    Activations Density 0.002%

    No Known Activations