© 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. 15-LLAMASCOPE-RES-131K
    11. 86995
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with measurements or data

    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
    Ïĥμο
    -0.07
    reject
    -0.06
    ptest
    -0.06
    tp
    -0.06
    pref
    -0.06
    kee
    -0.06
    ute
    -0.06
    ient
    -0.06
    ullo
    -0.06
    pers
    -0.06
    POSITIVE LOGITS
    000
    0.07
    ĶĶ
    0.06
    isor
    0.06
    Įĵ
    0.06
    gor
    0.06
    .Areas
    0.06
    UBLIC
    0.05
    viÄį
    0.05
    arer
    0.05
     ضÙĪ
    0.05
    Activations Density 0.051%

    No Known Activations