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. 17-LLAMASCOPE-RES-32K
    6. 12421
    Prev
    Next
    INDEX
    Explanations

    references to applications and their features across different platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifest
    -0.15
    بÙĪØ§Ø³Ø·Ø©
    -0.15
    leigh
    -0.14
     гоÑģп
    -0.14
    ève
    -0.14
    stva
    -0.14
    )":
    -0.14
    endet
    -0.14
    legg
    -0.14
    нÑİ
    -0.13
    POSITIVE LOGITS
    nam
    0.35
    :
    0.34
     viz
    0.30
     namely
    0.28
    viz
    0.26
    åĪĨåĪ«
    0.22
    :↵
    0.21
     including
    0.20
     nam
    0.20
     such
    0.19
    Activations Density 0.335%

    No Known Activations