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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 29-LLAMASCOPE-RES-32K
    6. 17975
    Prev
    Next
    INDEX
    Explanations

    phrases related to winning and gambling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zell
    -0.17
    oct
    -0.15
    де
    -0.14
    ยà¸ĩ
    -0.14
     unde
    -0.14
    -r
    -0.14
    ž
    -0.13
    erval
    -0.13
    İN
    -0.13
    §
    -0.13
    POSITIVE LOGITS
    -Allow
    0.31
    -Regular
    0.27
    -Methods
    0.26
    -Token
    0.25
    -Compatible
    0.24
    -Length
    0.24
    -
    0.23
    -Mobile
    0.23
    -Mail
    0.23
    -Ass
    0.23
    Activations Density 0.141%

    No Known Activations