Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-LLAMASCOPE-RES-32K
    6. 20988
    Prev
    Next
    INDEX
    Explanations

    phrases indicating prohibitions or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IOR
    -0.17
    .mdl
    -0.15
     ben
    -0.15
    ButtonItem
    -0.15
    ibbon
    -0.14
    ίδα
    -0.13
    ά
    -0.13
    posable
    -0.13
    aday
    -0.13
    _nullable
    -0.13
    POSITIVE LOGITS
    ep
    0.17
    -touch
    0.16
     Simpson
    0.16
    å¾
    0.15
     Pic
    0.15
     any
    0.15
    oice
    0.14
     Zone
    0.14
    åīĩ
    0.14
     use
    0.14
    Activations Density 0.146%

    No Known Activations