© 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. 93891
    Prev
    Next
    INDEX
    Explanations

    references to increasing amounts or intensities of something

    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
    lsen
    -0.08
    adle
    -0.07
    ằm
    -0.07
    /goto
    -0.06
    p
    -0.06
    _pins
    -0.06
    fty
    -0.06
    ÎŃλ
    -0.06
    por
    -0.06
    å½¹
    -0.06
    POSITIVE LOGITS
     Ramp
    0.07
    aging
    0.07
    sterdam
    0.07
    ement
    0.07
    zzo
    0.07
    аÑİ
    0.06
    ycin
    0.06
    egie
    0.06
    yr
    0.06
    rada
    0.06
    Activations Density 0.002%

    No Known Activations