© 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. 75384
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical records and military commemorations

    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
    :>
    -0.07
     explo
    -0.06
    itm
    -0.06
    indsight
    -0.06
    elian
    -0.06
    arto
    -0.06
     binh
    -0.06
    .scalablytyped
    -0.06
    ILES
    -0.06
     Marr
    -0.06
    POSITIVE LOGITS
    anti
    0.07
     (&
    0.07
    ison
    0.07
    ÄįnÃŃ
    0.07
    [s
    0.06
    Ì
    0.06
    ç¢
    0.06
    бÑĢа
    0.06
     addCriterion
    0.06
    matcher
    0.06
    Activations Density 0.013%

    No Known Activations