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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 30-LLAMASCOPE-RES-32K
    6. 22660
    Prev
    Next
    INDEX
    Explanations

    concepts related to decision-making, comparison, and conditions for acceptability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    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¸ĢåĪĩ
    -0.15
    äºĽ
    -0.13
    Ïģο
    -0.12
    outil
    -0.12
     sexle
    -0.12
     ragaz
    -0.11
     Prostitutas
    -0.11
     wszyst
    -0.11
    NullOr
    -0.11
    oleÄį
    -0.11
    POSITIVE LOGITS
     a
    0.93
     an
    0.71
    	a
    0.48
    a
    0.46
    ä¸Ģ个
    0.44
    ,a
    0.43
    )a
    0.39
    _a
    0.39
    ä¸ĢåĢĭ
    0.36
     another
    0.35
    Activations Density 6.982%

    No Known Activations