© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 23531
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and significant names

    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
    yb
    -0.15
    asio
    -0.15
    HOLDER
    -0.14
    ifer
    -0.14
    noc
    -0.14
    å¥
    -0.14
    roman
    -0.14
    etooth
    -0.14
     pedest
    -0.14
    otel
    -0.14
    POSITIVE LOGITS
     Mah
    0.23
    Mah
    0.21
     mah
    0.19
    mah
    0.17
    koli
    0.16
    æĤŁ
    0.15
    990
    0.15
    á»ĵi
    0.15
    oday
    0.14
     dol
    0.14
    Activations Density 0.014%

    No Known Activations