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. 9-LLAMASCOPE-RES-32K
    6. 2737
    Prev
    Next
    INDEX
    Explanations

    references to markets and market-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osate
    -0.16
     kå
    -0.16
     cust
    -0.16
     confer
    -0.15
    hl
    -0.15
     Toro
    -0.14
    /he
    -0.14
     Lig
    -0.14
    uds
    -0.14
     syn
    -0.13
    POSITIVE LOGITS
    aber
    0.17
    ourcem
    0.16
    Venue
    0.15
     rodin
    0.15
    LOOP
    0.15
    pec
    0.15
    adoo
    0.15
    ofday
    0.15
    utta
    0.14
    /Area
    0.14
    Activations Density 0.051%

    No Known Activations