© 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. 24-LLAMASCOPE-RES-32K
    11. 16891
    Prev
    Next
    INDEX
    Explanations

    Various forms of the word "ok" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anca
    -0.16
    ADOR
    -0.16
    addy
    -0.15
    adors
    -0.15
    encer
    -0.15
    ÑģÑĤво
    -0.15
     ëĭ¬
    -0.15
    akers
    -0.15
    ascar
    -0.15
    PLY
    -0.15
    POSITIVE LOGITS
    tober
    0.33
    lahoma
    0.31
    ahoma
    0.23
    amoto
    0.22
    anagan
    0.21
    lah
    0.21
    hots
    0.19
    änd
    0.19
    ays
    0.18
     Ok
    0.18
    Activations Density 0.021%

    No Known Activations