INDEX

Explanations

phrases indicating uncertainty or hesitation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ä¸ļ

-0.17

cken

-0.16

plen

-0.14

Î´Î¬

-0.14

retty

-0.14

 svÄĽ

-0.14

jez

-0.13

 regards

-0.13

inic

-0.13

 Tight

-0.13

POSITIVE LOGITS

 dwelling

0.21

 bore

0.21

 Into

0.18

 spoiler

0.18

 detail

0.18

 boring

0.18

Into

0.17

 labour

0.17

 into

0.17

dig

0.17

Activations Density 0.094%

phrases indicating uncertainty or hesitation

No Comments

No Known Activations