© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 74940
    Prev
    Next
    INDEX
    Explanations

    instances of the character sequence "—"

    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
     kabil
    -0.08
    bish
    -0.06
    .tpl
    -0.06
     Spit
    -0.06
    OUS
    -0.06
     slur
    -0.06
    incident
    -0.06
    apos
    -0.06
    лÑĥ
    -0.06
    ÑģÑı
    -0.06
    POSITIVE LOGITS
    ano
    0.07
    ————————————————
    0.07
    ANO
    0.07
    984
    0.06
    à¥Ģà¤Ł
    0.06
    amu
    0.06
    ãİ
    0.06
    ————————
    0.06
    LEGRO
    0.06
     getFile
    0.06
    Activations Density 0.018%

    No Known Activations