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. 23-LLAMASCOPE-RES-32K
    6. 12366
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant events or actions related to injury or recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iap
    -0.14
    utin
    -0.13
    ायत
    -0.13
    볤
    -0.12
    .foundation
    -0.12
    alach
    -0.12
     beforehand
    -0.12
    ëħĦìĹIJëĬĶ
    -0.12
    AndWait
    -0.12
    attles
    -0.12
    POSITIVE LOGITS
     after
    1.13
    after
    0.91
     поÑģле
    0.81
     dopo
    0.80
     After
    0.79
    After
    0.76
    _after
    0.75
     AFTER
    0.74
    -after
    0.71
     пÑĸÑģлÑı
    0.70
    Activations Density 0.943%

    No Known Activations