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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-LLAMASCOPE-RES-32K
    6. 25339
    Prev
    Next
    INDEX
    Explanations

    mentions of firefighting, rescue efforts, and related emergency services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAIN
    -0.19
    .Magenta
    -0.17
    ãĥ¼ãĥī
    -0.16
    éŀ
    -0.15
    rove
    -0.15
    agenta
    -0.14
    edla
    -0.14
    æľ
    -0.14
    ãĥ¼ãĤ¸
    -0.14
    ethnic
    -0.13
    POSITIVE LOGITS
    lü
    0.16
     Blackburn
    0.15
     medical
    0.15
    412
    0.14
    itted
    0.14
    apon
    0.14
     Gerr
    0.13
     Bookmark
    0.13
    meer
    0.13
     manuals
    0.13
    Activations Density 0.337%

    No Known Activations