© 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. 23-LLAMASCOPE-RES-32K
    11. 836
    Prev
    Next
    INDEX
    Explanations

    expressions related to consumer and financial anxiety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ
    -0.14
    eo
    -0.14
    [s
    -0.14
    Plate
    -0.13
     Chi
    -0.13
     gadgets
    -0.13
    æĹı
    -0.13
    erten
    -0.13
    los
    -0.13
    alam
    -0.13
    POSITIVE LOGITS
    루
    0.16
    μεν
    0.15
    iterated
    0.15
    åı
    0.14
    opsy
    0.14
    nP
    0.14
    dech
    0.14
    amon
    0.14
    651
    0.14
    uve
    0.14
    Activations Density 0.125%

    No Known Activations