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. 29-LLAMASCOPE-RES-32K
    6. 3542
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "letter" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yas
    -0.17
    emaker
    -0.17
    ARDS
    -0.15
    sale
    -0.15
    yum
    -0.15
    лÑıн
    -0.15
    slu
    -0.15
    zdy
    -0.15
    yan
    -0.15
    yor
    -0.14
    POSITIVE LOGITS
    press
    0.31
    head
    0.28
    atura
    0.22
    ing
    0.21
     addressed
    0.21
    ed
    0.20
    /email
    0.20
    -writing
    0.19
     sent
    0.19
    headed
    0.19
    Activations Density 0.025%

    No Known Activations