Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 8-LLAMASCOPE-RES-32K
    6. 22780
    Prev
    Next
    INDEX
    Explanations

    instances of the word "unfortunately."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conserv
    -0.15
    vim
    -0.15
     Pu
    -0.14
    ür
    -0.14
    cono
    -0.14
    nte
    -0.14
     synonym
    -0.14
    ve
    -0.14
    und
    -0.13
    ñana
    -0.13
    POSITIVE LOGITS
    çe
    0.17
    nop
    0.16
    ably
    0.16
    robe
    0.15
    &action
    0.15
    uce
    0.14
    611
    0.14
    805
    0.14
    _lift
    0.14
    ìľ¼
    0.14
    Activations Density 0.016%

    No Known Activations