© 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. 17-LLAMASCOPE-RES-131K
    11. 15952
    Prev
    Next
    INDEX
    Explanations

    XML attribute names

    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
    fts
    -0.07
    estre
    -0.07
    VS
    -0.07
     /*č↵
    -0.07
    inton
    -0.07
    annonce
    -0.07
    ,ev
    -0.07
    ég
    -0.06
    omanip
    -0.06
     Puzzle
    -0.06
    POSITIVE LOGITS
    adro
    0.07
    ibase
    0.06
     Sed
    0.06
    hausen
    0.06
    undle
    0.06
    _Unit
    0.06
     USHORT
    0.06
     UCHAR
    0.06
    ì£ł
    0.06
     Sau
    0.06
    Activations Density 0.000%

    No Known Activations