© 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. 27-LLAMASCOPE-RES-32K
    11. 2129
    Prev
    Next
    INDEX
    Explanations

    punctuations and transitional phrases indicating argument flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.17
    eling
    -0.15
    oran
    -0.14
    _Impl
    -0.14
    arella
    -0.14
    erva
    -0.14
    à¸Īะà¹Ħà¸Ķ
    -0.14
    åĴ²
    -0.14
    phis
    -0.13
    pressions
    -0.13
    POSITIVE LOGITS
     Fol
    0.20
    esel
    0.19
    Attempt
    0.16
    åĬ¡
    0.16
     exactly
    0.16
    à¥ģण
    0.15
     Bene
    0.14
    remen
    0.14
    åIJ¯
    0.14
     inch
    0.14
    Activations Density 0.065%

    No Known Activations