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. 23-LLAMASCOPE-RES-32K
    6. 28351
    Prev
    Next
    INDEX
    Explanations

    patterns of aspiration and collaboration towards achieving goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogn
    -0.15
    ãĤ¡
    -0.13
     ########################################################################
    -0.12
    agina
    -0.12
    .CreateInstance
    -0.12
    ìĿ¸ì§Ģ
    -0.11
    atial
    -0.11
    _:*
    -0.11
    andex
    -0.11
     además
    -0.11
    POSITIVE LOGITS
     same
    1.40
    same
    1.26
    Same
    1.10
     Same
    1.09
     similar
    1.01
     SAME
    1.01
    åIJĮ
    0.98
    _same
    0.96
    缸åIJĮ
    0.95
     similarly
    0.92
    Activations Density 2.148%

    No Known Activations