© 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. 2-LLAMASCOPE-RES-32K
    11. 3026
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals named Andrew, particularly Andrew Martin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eland
    -0.17
    ipo
    -0.16
    ular
    -0.16
    ̧
    -0.16
    uing
    -0.14
    grounds
    -0.14
    PIO
    -0.14
    ÑĢд
    -0.14
    imo
    -0.14
    andro
    -0.14
    POSITIVE LOGITS
    /or
    0.14
    ÙĥÙĪر
    0.14
    ither
    0.13
    ship
    0.13
    rors
    0.13
    alls
    0.13
    Gate
    0.13
    odge
    0.13
    uD
    0.13
    ikers
    0.13
    Activations Density 0.009%

    No Known Activations