© 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. 22-LLAMASCOPE-RES-131K
    6. 3723
    Prev
    Next
    INDEX
    Explanations

    direct quotes and references to statements made by public figures, particularly in a political context

    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
    itler
    -0.06
    ynom
    -0.06
    linger
    -0.06
    ÑĢÑĮ
    -0.06
     ÑįÑĤ
    -0.06
    achie
    -0.06
    ãģµ
    -0.06
    ekl
    -0.06
    _sz
    -0.06
    zcze
    -0.06
    POSITIVE LOGITS
    acro
    0.07
    анÑĤаж
    0.07
     Fake
    0.06
     Witch
    0.06
    .Attributes
    0.06
    à¥įतव
    0.06
    &E
    0.06
    ORMAT
    0.06
     пÑĥ
    0.06
     Wake
    0.06
    Activations Density 0.017%

    No Known Activations