© 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. 77418
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and journeys

    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
    ĮĴ
    -0.07
    åĩºåİ»
    -0.07
    ForObject
    -0.07
    ecs
    -0.06
    vely
    -0.06
    goog
    -0.06
     Kut
    -0.06
    оÑĩÑĮ
    -0.06
    ãĥ©ãĤ¤ãĥĪ
    -0.06
    ieux
    -0.06
    POSITIVE LOGITS
     return
    0.23
     returning
    0.22
     returned
    0.22
    return
    0.22
    åĽŀæĿ¥
    0.21
     returns
    0.19
    returned
    0.19
    è¿ĶåĽŀ
    0.19
     Return
    0.18
    Return
    0.18
    Activations Density 0.069%

    No Known Activations