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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119391
    Prev
    Next
    INDEX
    Explanations

    mentions of dates and numerical values

    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
    lazy
    -0.06
    rz
    -0.06
     coping
    -0.06
    ett
    -0.06
    زار
    -0.06
    TestingModule
    -0.06
    оÑģÑĢед
    -0.05
    ahun
    -0.05
    ä¼ij
    -0.05
    lio
    -0.05
    POSITIVE LOGITS
    skirts
    0.08
    Ø¡
    0.07
    usb
    0.06
    δÏħ
    0.06
    iras
    0.06
    мини
    0.06
    (EXPR
    0.06
     Dawn
    0.06
    DownList
    0.06
    áh
    0.06
    Activations Density 0.020%

    No Known Activations