© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-32K
    6. 3183
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the inclusion of resources or information for the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perator
    -0.15
    rance
    -0.15
    itter
    -0.15
    Ø´Ùħ
    -0.14
     Wr
    -0.14
    sh
    -0.13
    187
    -0.13
    caff
    -0.13
    eler
    -0.13
    asted
    -0.13
    POSITIVE LOGITS
    ÏĩÏİ
    0.16
    argar
    0.15
    aoke
    0.15
    /GPL
    0.15
    bable
    0.15
    activex
    0.15
    quito
    0.14
    ÏĦÏģο
    0.14
    ftime
    0.14
    oload
    0.14
    Activations Density 0.294%

    No Known Activations