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. 30-LLAMASCOPE-RES-32K
    6. 16989
    Prev
    Next
    INDEX
    Explanations

    references to food and drink combinations in a casual context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstantiationException
    -0.17
    ustin
    -0.16
    otlin
    -0.15
    è·Ŀ
    -0.15
    fried
    -0.15
    ipeg
    -0.15
    avage
    -0.15
    .jav
    -0.14
    chemist
    -0.14
    lsruhe
    -0.14
    POSITIVE LOGITS
     dashes
    0.23
     Ang
    0.23
     Fee
    0.22
     gren
    0.22
     Pey
    0.21
     Gall
    0.20
     simple
    0.20
     Camp
    0.20
     Chart
    0.20
    Fee
    0.19
    Activations Density 0.013%

    No Known Activations