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. 146
    Prev
    Next
    INDEX
    Explanations

    formatting and structural elements typically found in code or technical documentation

    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
    akh
    -0.15
    atalog
    -0.15
    itten
    -0.15
    CHIP
    -0.15
    amera
    -0.15
    acha
    -0.14
    urette
    -0.14
    cmc
    -0.14
    веÑĢ
    -0.14
    iyah
    -0.14
    POSITIVE LOGITS
    -strokes
    0.18
     Voll
    0.16
    ãĥªãĤ«
    0.14
    rellas
    0.14
    teki
    0.14
    丶
    0.14
    stal
    0.14
    ãĤ¿ãĥ«
    0.14
    983
    0.13
    tabl
    0.13
    Activations Density 0.049%

    No Known Activations