© 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. 23-LLAMASCOPE-RES-32K
    11. 29481
    Prev
    Next
    INDEX
    Explanations

    expressions related to requests for information or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paring
    -0.15
    éĸ
    -0.15
    uche
    -0.15
    itre
    -0.15
    _ASSUME
    -0.14
    èµŀ
    -0.14
    cilik
    -0.14
    461
    -0.14
    å®ı
    -0.14
    /Instruction
    -0.14
    POSITIVE LOGITS
     answers
    0.37
     concrete
    0.31
     official
    0.30
     answer
    0.28
     update
    0.27
     updates
    0.27
     resolution
    0.27
     progress
    0.27
     firm
    0.27
     word
    0.27
    Activations Density 0.153%

    No Known Activations