© 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. 128019
    Prev
    Next
    INDEX
    Explanations

    the presence of eBooks and digital content references

    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
    anus
    -0.06
    oit
    -0.06
    ingu
    -0.06
    æĶ¯
    -0.06
    avern
    -0.06
    nila
    -0.06
     Derrick
    -0.06
    åIJİçļĦ
    -0.06
    овеÑĢ
    -0.06
    igel
    -0.06
    POSITIVE LOGITS
    aterangepicker
    0.07
     reading
    0.07
    istrovstvÃŃ
    0.07
    åľ¨çº¿éĺħ读
    0.07
    OOK
    0.06
    ahoo
    0.06
     Mö
    0.06
    Ù쨧ÙĤ
    0.06
    wdx
    0.06
    å¶
    0.06
    Activations Density 0.000%

    No Known Activations