© 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. 27-LLAMASCOPE-RES-32K
    11. 12705
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to networking and professional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asio
    -0.14
    rieb
    -0.14
    arel
    -0.14
    iras
    -0.14
    ivant
    -0.13
     Naked
    -0.13
    roulette
    -0.13
    ÙĨز
    -0.13
    verity
    -0.13
     marg
    -0.13
    POSITIVE LOGITS
     network
    0.95
     networks
    0.81
    network
    0.78
     Network
    0.75
    -network
    0.72
    Network
    0.70
     NETWORK
    0.69
    _network
    0.68
    ç½ij绾
    0.67
     Networks
    0.65
    Activations Density 0.190%

    No Known Activations