© 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. 26614
    Prev
    Next
    INDEX
    Explanations

    references to specific titles or works, especially in the context of literature and media

    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
    -0.08
     ref
    -0.06
     motto
    -0.06
     mj
    -0.06
    SJ
    -0.05
    det
    -0.05
    prd
    -0.05
    dat
    -0.05
     =
    -0.05
     (
    -0.05
    POSITIVE LOGITS
    ÐIJÑĢÑħÑĸв
    0.09
    URLException
    0.08
    бÑĥдÑĮ
    0.08
    (íģ¬ê¸°
    0.08
    «a
    0.07
    .rar
    0.07
    ÑģлÑĸд
    0.07
    галÑĸ
    0.07
    _named
    0.07
     FieldType
    0.07
    Activations Density 0.005%

    No Known Activations