© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125081
    Prev
    Next
    INDEX
    Explanations

    references to statistical or quantitative 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
     stuff
    -0.08
    Qed
    -0.07
    ewise
    -0.07
    IGHLIGHT
    -0.07
     ÐĿаÑģеление
    -0.07
    esar
    -0.07
    owa
    -0.07
    ufen
    -0.07
     _
    -0.06
    ffen
    -0.06
    POSITIVE LOGITS
    wap
    0.08
    olesale
    0.06
    azi
    0.06
    theid
    0.06
    CMS
    0.06
     Mey
    0.06
    cling
    0.06
    uer
    0.05
    .::
    0.05
     Firstly
    0.05
    Activations Density 0.000%

    No Known Activations