INDEX

Explanations

phrases that express hypothetical situations or conditional thoughts

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

plor

-0.17

insky

-0.15

oka

-0.15

-heading

-0.14

oplay

-0.14

ç´

-0.14

ä»¤

-0.14

ãĥ¼ãĥĲ

-0.14

XR

-0.13

agh

-0.13

POSITIVE LOGITS

 think

0.29

 THINK

0.28

 thinks

0.26

 Think

0.26

 thinking

0.26

 thought

0.25

Think

0.25

think

0.24

 expects

0.24

 expect

0.23

Activations Density 0.032%

phrases that express hypothetical situations or conditional thoughts

No Comments

No Known Activations