© 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. 30-LLAMASCOPE-RES-32K
    11. 5172
    Prev
    Next
    INDEX
    Explanations

    variations of the word "tow" and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quist
    -0.15
    idency
    -0.15
    ourn
    -0.15
    walker
    -0.15
    strar
    -0.15
    GetInt
    -0.14
    ->__
    -0.14
    vection
    -0.14
    REAM
    -0.14
    alnız
    -0.14
    POSITIVE LOGITS
    headed
    0.22
    ard
    0.21
    anda
    0.21
    eling
    0.20
    path
    0.20
    NS
    0.20
    erview
    0.19
     truck
    0.19
    elled
    0.19
    els
    0.18
    Activations Density 0.008%

    No Known Activations