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. 12-LLAMASCOPE-RES-32K
    6. 19753
    Prev
    Next
    INDEX
    Explanations

    references to used car models for sale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etta
    -0.15
    fik
    -0.15
     adipiscing
    -0.15
    UNUSED
    -0.14
    engo
    -0.14
    êu
    -0.14
    .XR
    -0.13
    ridor
    -0.13
     ntohs
    -0.13
    essa
    -0.13
    POSITIVE LOGITS
     Kelley
    0.13
    mediately
    0.13
    mom
    0.13
     Sher
    0.13
     Priority
    0.12
     quil
    0.12
    endir
    0.12
     Holt
    0.12
    IgnoreCase
    0.12
     Slee
    0.12
    Activations Density 0.000%

    No Known Activations