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. 4-LLAMASCOPE-RES-32K
    6. 26643
    Prev
    Next
    INDEX
    Explanations

    patterns related to decimal numbers and their formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arhus
    -0.17
    ufs
    -0.16
    ander
    -0.16
    acas
    -0.14
    antan
    -0.14
    olle
    -0.14
    yes
    -0.14
    éry
    -0.14
    غاÙĨ
    -0.14
    .boolean
    -0.14
    POSITIVE LOGITS
    ransition
    0.14
    rss
    0.14
    ress
    0.14
    åŀĤ
    0.14
    pt
    0.14
    ptype
    0.13
     Cue
    0.13
    atur
    0.13
     pedigree
    0.13
     Equals
    0.13
    Activations Density 0.105%

    No Known Activations