Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 7-LLAMASCOPE-RES-32K
    6. 17672
    Prev
    Next
    INDEX
    Explanations

    the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ukan
    -0.16
    ajo
    -0.15
    ãĥĥãĥĦ
    -0.15
    ìĭľìĺ¤
    -0.15
    ssl
    -0.15
     terminal
    -0.15
    ç»Ī
    -0.15
    aÄį
    -0.14
    spaces
    -0.14
    ãĤ¦ãĥ³
    -0.14
    POSITIVE LOGITS
    quot
    0.17
    /OR
    0.15
    /or
    0.15
    è£ķ
    0.14
    maf
    0.13
    chers
    0.13
    ackers
    0.13
    ippet
    0.13
    missive
    0.13
    phan
    0.13
    Activations Density 0.033%

    No Known Activations