© 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. 76783
    Prev
    Next
    INDEX
    Explanations

    references to "Real" in various contexts

    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
    ello
    -0.08
    etta
    -0.08
    eting
    -0.07
    reste
    -0.07
    ectomy
    -0.07
     XCT
    -0.07
    esch
    -0.06
    eldorf
    -0.06
    /weather
    -0.06
    ect
    -0.06
    POSITIVE LOGITS
    istically
    0.09
    istic
    0.09
    ito
    0.08
    onda
    0.08
    igned
    0.08
    ignment
    0.08
     McCoy
    0.08
    tek
    0.08
    abs
    0.07
    izations
    0.07
    Activations Density 0.009%

    No Known Activations