© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1487
    Prev
    Next
    INDEX
    Explanations

    citations or references to academic articles and their bibliographic details

    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
     Nam
    -0.07
    çĨ
    -0.06
    hack
    -0.06
     Hack
    -0.06
     curve
    -0.06
    isto
    -0.06
     Ch
    -0.06
    _UNIX
    -0.05
    rets
    -0.05
    557
    -0.05
    POSITIVE LOGITS
    Cipher
    0.07
    ORA
    0.07
    _unset
    0.07
    éru
    0.06
    .intellij
    0.06
    .poi
    0.06
     Král
    0.06
    <Scalar
    0.06
    cased
    0.06
     μÎŃÏģοÏĤ
    0.06
    Activations Density 0.003%

    No Known Activations