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. 28-LLAMASCOPE-RES-32K
    6. 623
    Prev
    Next
    INDEX
    Explanations

    terms related to drainage and water management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     drugs
    -0.20
    ikat
    -0.19
     Drugs
    -0.19
    amd
    -0.16
    stretch
    -0.16
     drug
    -0.16
    ior
    -0.15
    rael
    -0.15
     drinkers
    -0.15
     drink
    -0.15
    POSITIVE LOGITS
    age
    0.23
    pipes
    0.18
    pipe
    0.18
    aper
    0.17
    amage
    0.16
    alin
    0.16
    ondheim
    0.15
    aggable
    0.15
    alytics
    0.15
    aine
    0.15
    Activations Density 0.036%

    No Known Activations