© 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. 24-LLAMASCOPE-RES-32K
    11. 15098
    Prev
    Next
    INDEX
    Explanations

    instances of the word "opt" and its variations, indicating choices or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tha
    -0.19
    IED
    -0.18
    enk
    -0.16
    getc
    -0.15
    piece
    -0.15
    ly
    -0.15
    reu
    -0.14
    igel
    -0.14
    rna
    -0.14
    -même
    -0.14
    POSITIVE LOGITS
    -out
    0.22
    opt
    0.20
    imize
    0.20
     opt
    0.17
    -Out
    0.17
    :selected
    0.17
     Opt
    0.17
    /opt
    0.16
     out
    0.16
    entimes
    0.16
    Activations Density 0.006%

    No Known Activations