© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40592
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and experimental data

    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
    è®®
    -0.06
     compens
    -0.06
     thought
    -0.06
     big
    -0.06
     report
    -0.06
     Type
    -0.05
    arda
    -0.05
    bec
    -0.05
    adal
    -0.05
     so
    -0.05
    POSITIVE LOGITS
    лÑıли
    0.08
    инов
    0.08
    ãİ
    0.08
    ocz
    0.07
    ãĥįãĥ«
    0.07
    ohl
    0.07
    olib
    0.07
    ChangeEvent
    0.07
    duit
    0.07
    ENDIF
    0.07
    Activations Density 0.124%

    No Known Activations