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. 15-LLAMASCOPE-RES-32K
    6. 23719
    Prev
    Next
    INDEX
    Explanations

    phrases related to preparation and justification in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enberg
    -0.15
    aname
    -0.14
    AffineTransform
    -0.14
     "<?
    -0.14
    orks
    -0.14
    ayah
    -0.14
     Trouble
    -0.13
    dash
    -0.13
    ovie
    -0.13
    nÄĽt
    -0.13
    POSITIVE LOGITS
    ilden
    0.14
    ullet
    0.14
    udi
    0.14
    ãĤ¹ãĥļ
    0.13
    ors
    0.13
     Wich
    0.13
    oin
    0.13
    åİ»äºĨ
    0.13
    æĺ¯æĪij
    0.12
    plural
    0.12
    Activations Density 0.004%

    No Known Activations