© 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. 11320
    Prev
    Next
    INDEX
    Explanations

    terms related to substitution and suburban themes

    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
    ython
    -0.18
    chet
    -0.16
    chers
    -0.16
    obl
    -0.16
    izr
    -0.16
    ighton
    -0.16
    obre
    -0.16
     عص
    -0.15
    stride
    -0.15
    nia
    -0.15
    POSITIVE LOGITS
    =sub
    0.26
    (Sub
    0.25
    /Sub
    0.25
    /sub
    0.24
    stract
    0.23
    -Saharan
    0.20
    istence
    0.19
    (sub
    0.19
    mers
    0.18
    ordinates
    0.18
    Activations Density 0.073%

    No Known Activations