INDEX

Explanations

examples illustrating key concepts or principles

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_iff

-0.16

rieve

-0.14

istrovstvÃŃ

-0.13

ãģ¯ãģļ

-0.13

erialize

-0.13

riminator

-0.12

Crud

-0.12

áº¡ch

-0.12

heim

-0.12

isser

-0.12

POSITIVE LOGITS

 example

0.86

 examples

0.82

example

0.68

ä¾ĭ

0.67

 Examples

0.66

examples

0.66

 Example

0.65

 exemple

0.63

 exemp

0.62

 EXAMPLE

0.60

Activations Density 0.608%

examples illustrating key concepts or principles

No Comments

No Known Activations