© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 22202
    Prev
    Next
    INDEX
    Explanations

    instances of the word "any" and related phrases indicating uncertainty or lack of specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĢäºĽ
    -0.21
     Numerous
    -0.18
    anzi
    -0.17
     Various
    -0.17
    اتÛĮ
    -0.16
     einige
    -0.16
    rick
    -0.16
     some
    -0.15
     Several
    -0.15
     everywhere
    -0.15
    POSITIVE LOGITS
     sort
    0.31
    /all
    0.29
    ones
    0.26
     further
    0.26
     kind
    0.26
     particular
    0.25
    thin
    0.24
    kind
    0.23
    THING
    0.23
    ht
    0.22
    Activations Density 0.076%

    No Known Activations