© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 18-LLAMASCOPE-RES-32K
    6. 23584
    Prev
    Next
    INDEX
    Explanations

    connections to various medical conditions, particularly focusing on their diagnosis, symptoms, and the absence of cures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stranger
    -0.16
    ниÑĨ
    -0.14
    иÑĩеÑģкое
    -0.14
    474
    -0.14
    ign
    -0.13
    422
    -0.13
    ante
    -0.13
    ve
    -0.13
     Forgotten
    -0.13
    ugg
    -0.13
    POSITIVE LOGITS
     there
    0.31
     no
    0.31
     There
    0.27
    there
    0.24
    There
    0.24
     THERE
    0.24
     неÑĤ
    0.23
    ä¸įåŃĺåľ¨
    0.22
    no
    0.21
     nobody
    0.21
    Activations Density 0.220%

    No Known Activations