© 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. 28-LLAMASCOPE-RES-32K
    11. 20841
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "out" and its variations in contexts suggesting consequence or resolution

    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
    grily
    -0.21
    ÏĦα
    -0.18
    ulously
    -0.18
    sembled
    -0.17
    MX
    -0.16
    ån
    -0.16
    sembly
    -0.16
    mente
    -0.15
    mary
    -0.15
    587
    -0.15
    POSITIVE LOGITS
    lay
    0.25
    mod
    0.25
    -of
    0.22
    flow
    0.21
    pour
    0.21
    growth
    0.21
    crop
    0.21
    cast
    0.20
     loud
    0.20
    ages
    0.20
    Activations Density 0.041%

    No Known Activations