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. 3-LLAMASCOPE-RES-32K
    6. 16579
    Prev
    Next
    INDEX
    Explanations

    references to do-it-yourself (DIY) projects and crafts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ī
    -0.17
    oggler
    -0.16
    herits
    -0.16
    ģn
    -0.16
    zet
    -0.15
    Ñĥди
    -0.14
    ngth
    -0.14
     Kral
    -0.14
     Drill
    -0.14
    ctype
    -0.14
    POSITIVE LOGITS
    инкÑĥ
    0.16
    entine
    0.15
    luv
    0.15
    imon
    0.15
    наÑħ
    0.14
    contributors
    0.14
    doch
    0.14
     Dag
    0.14
    lsa
    0.14
    uper
    0.13
    Activations Density 0.641%

    No Known Activations