© 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. 105814
    Prev
    Next
    INDEX
    Explanations

    negative phrasing indicating doubts or denials in arguments

    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
    inho
    -0.07
     void
    -0.07
     sandwich
    -0.07
    Äĥng
    -0.06
    vez
    -0.06
     Paid
    -0.06
     blah
    -0.06
    ÃŃd
    -0.06
    è¼
    -0.06
    kem
    -0.06
    POSITIVE LOGITS
    .cx
    0.07
    ìĦŃ
    0.06
     Gilbert
    0.06
    ê·ł
    0.06
    556
    0.06
    íĻĪ
    0.06
    ::::::
    0.06
    ENSE
    0.06
    ÑĥлÑı
    0.06
    à¥Ĥत
    0.06
    Activations Density 0.027%

    No Known Activations