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. 22347
    Prev
    Next
    INDEX
    Explanations

    descriptors related to flavor profiles and characteristics of beverages, particularly whiskeys

    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
    ãĥĸãĥ«
    -0.16
    ÑĢеб
    -0.16
    elong
    -0.15
    æ¾
    -0.15
    parate
    -0.14
    -BEGIN
    -0.14
    boro
    -0.14
    996
    -0.14
    icode
    -0.14
    gem
    -0.14
    POSITIVE LOGITS
     tobacco
    0.22
     leather
    0.21
     hints
    0.21
     touches
    0.21
     pipe
    0.20
     earth
    0.20
     lic
    0.20
     baking
    0.20
     clo
    0.20
     baker
    0.20
    Activations Density 0.018%

    No Known Activations