© 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 EvalsExportsinterp-engineNEWAPI 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. 92385
    Prev
    Next
    INDEX
    Explanations

    elements related to evaluation and measurement 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
    abcdefghijklmnop
    -0.09
    olec
    -0.08
    _aliases
    -0.08
    imler
    -0.08
    ierz
    -0.08
    anness
    -0.07
    åļ
    -0.07
    omentum
    -0.07
    hlas
    -0.07
    ’ta
    -0.07
    POSITIVE LOGITS
     aspect
    0.08
     aspects
    0.07
    tons
    0.07
    atz
    0.06
     physical
    0.06
     temperature
    0.06
     parental
    0.06
    finity
    0.06
    pects
    0.06
    oice
    0.06
    Activations Density 0.133%

    No Known Activations