© 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. 56469
    Prev
    Next
    INDEX
    Explanations

    specific software and server-related terms or versions

    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
     offensive
    -0.06
     Offensive
    -0.06
     kir
    -0.06
    anco
    -0.06
    uby
    -0.06
    ula
    -0.06
    agna
    -0.05
    stadt
    -0.05
    ÑĻ
    -0.05
    ido
    -0.05
    POSITIVE LOGITS
    ENU
    0.08
    iyan
    0.08
    imizer
    0.07
    atten
    0.07
    vfs
    0.07
    å°İ
    0.07
    #ac
    0.07
    atts
    0.07
    agent
    0.07
     product
    0.07
    Activations Density 0.032%

    No Known Activations