© 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. 20-LLAMASCOPE-RES-32K
    11. 21304
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate inquiries or requests for information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     answer
    -0.20
     Answer
    -0.20
     answering
    -0.19
    answer
    -0.17
    Answer
    -0.16
    åĽŀçŃĶ
    -0.15
    .answer
    -0.15
     notifying
    -0.15
     ANSW
    -0.14
    fty
    -0.14
    POSITIVE LOGITS
     asking
    0.42
     ask
    0.42
    ask
    0.41
     asks
    0.39
    asking
    0.38
    Ask
    0.38
    .ask
    0.37
     Ask
    0.36
    ASK
    0.34
     asked
    0.34
    Activations Density 0.305%

    No Known Activations