© 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. 22895
    Prev
    Next
    INDEX
    Explanations

    phrases related to future developments and advancements

    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
    alleries
    -0.15
    å·Ŀ
    -0.15
    lew
    -0.14
    ollo
    -0.14
    idlo
    -0.14
    .Generated
    -0.14
    ayer
    -0.14
    amik
    -0.13
    odate
    -0.13
    ajs
    -0.13
    POSITIVE LOGITS
     ahead
    0.54
    ahead
    0.49
     Ahead
    0.48
    Ahead
    0.41
     впеÑĢед
    0.35
     yet
    0.35
     coming
    0.34
    -ahead
    0.34
     forthcoming
    0.33
    yet
    0.31
    Activations Density 0.096%

    No Known Activations