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. 18-LLAMASCOPE-RES-32K
    6. 2618
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal rulings and the implications of law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    â̦↵
    -0.23
    â̦and
    -0.20
    â̦”
    -0.19
     [â̦]↵
    -0.19
     â̦↵
    -0.18
    â̦
    -0.18
    â̦"
    -0.17
    â̦the
    -0.17
    â̦â̦
    -0.17
    â̦.
    -0.17
    POSITIVE LOGITS
    /***/
    0.14
    #af
    0.13
    )frame
    0.12
    )application
    0.12
    >tag
    0.12
    #ab
    0.12
    #ad
    0.12
    UpInside
    0.12
    /******/
    0.12
    #ac
    0.11
    Activations Density 88.040%

    No Known Activations