© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 1548
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to Vue.js framework functionality

    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
     Wend
    -0.16
    sharp
    -0.14
    icari
    -0.14
     Schwar
    -0.14
    ADED
    -0.13
    xl
    -0.13
    .boolean
    -0.13
    hex
    -0.13
     MagicMock
    -0.13
    amer
    -0.13
    POSITIVE LOGITS
     super
    0.22
     Super
    0.21
    .super
    0.20
    Super
    0.19
    _SUPER
    0.19
    classCallCheck
    0.19
     SUPER
    0.19
    super
    0.18
    _super
    0.18
    	super
    0.16
    Activations Density 0.186%

    No Known Activations