© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 22414
    Prev
    Next
    INDEX
    Explanations

    phrases related to vehicle tuning and performance modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mlin
    -0.15
     Elastic
    -0.15
     Glo
    -0.15
    inite
    -0.14
    å°ĺ
    -0.14
     commercial
    -0.14
     bund
    -0.14
     punct
    -0.14
    burger
    -0.13
    Å¡ov
    -0.13
    POSITIVE LOGITS
     dyn
    0.27
    dyn
    0.25
     Performance
    0.24
     performance
    0.23
     street
    0.22
    Performance
    0.22
    Street
    0.22
     Street
    0.22
     tunes
    0.22
     tuning
    0.21
    Activations Density 0.063%

    No Known Activations