© 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. 21-LLAMASCOPE-RES-32K
    11. 9447
    Prev
    Next
    INDEX
    Explanations

    text that discusses modifications and variations in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÅĻeba
    -0.15
    /reset
    -0.14
     revived
    -0.14
     abruptly
    -0.13
     renewed
    -0.13
    lom
    -0.13
     suddenly
    -0.13
     restarted
    -0.13
     renewal
    -0.13
     resurgence
    -0.13
    POSITIVE LOGITS
     modifications
    0.42
     slight
    0.42
     slightly
    0.40
     modification
    0.38
     minor
    0.36
     Modifications
    0.34
     additions
    0.34
    ä¿®æĶ¹
    0.31
     modific
    0.31
     additional
    0.30
    Activations Density 0.336%

    No Known Activations