© 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. 15-LLAMASCOPE-RES-32K
    6. 6769
    Prev
    Next
    INDEX
    Explanations

    references to the existence or occurrence of entities and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tron
    -0.19
    sh
    -0.18
    lick
    -0.15
    torch
    -0.15
    ola
    -0.15
    enga
    -0.14
    pton
    -0.14
    omu
    -0.14
    ren
    -0.14
    itchen
    -0.14
    POSITIVE LOGITS
    Presence
    0.22
     Presence
    0.22
    iment
    0.22
     presence
    0.21
    presence
    0.20
    ational
    0.18
    entially
    0.18
    onym
    0.17
    ence
    0.17
    wahl
    0.16
    Activations Density 0.044%

    No Known Activations