INDEX

Explanations

instances of punctuation marks, particularly periods and question marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

laden

-0.16

dera

-0.15

ãģĨãĤĵ

-0.14

 Bowen

-0.14

IDI

-0.14

incident

-0.13

AGMA

-0.13

ÎºÎŃ

-0.13

lÃ¤

-0.13

ssa

-0.13

POSITIVE LOGITS

 maybe

0.21

 turn

0.17

Ð½ÑĸÐ²ÐµÑĢ

0.15

 Maybe

0.15

 Turn

0.14

Maybe

0.14

-turn

0.14

maybe

0.14

ongan

0.14

IEW

0.14

Activations Density 0.002%

instances of punctuation marks, particularly periods and question marks

No Comments

No Known Activations