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. 7-LLAMASCOPE-RES-32K
    6. 17597
    Prev
    Next
    INDEX
    Explanations

    expressions of regret or the desire to forget past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idal
    -0.15
     NOTIFY
    -0.14
    umbing
    -0.14
    eday
    -0.13
     selfish
    -0.13
    .wrap
    -0.13
    egrator
    -0.13
     treff
    -0.13
    bn
    -0.12
    stime
    -0.12
    POSITIVE LOGITS
    ple
    0.15
    anos
    0.15
     Stamp
    0.15
    ŀ
    0.14
    ÏĢλ
    0.14
    Stamp
    0.14
    rocket
    0.14
     stamp
    0.14
    ÑģÑĤоÑı
    0.14
    vel
    0.14
    Activations Density 0.299%

    No Known Activations