INDEX

Explanations

parentheses and parenthetical structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

amient

-0.16

mente

-0.16

tion

-0.15

eyn

-0.15

$__

-0.15

erguson

-0.14

ÐµÑĢÐ°Ð¿

-0.14

leet

-0.14

lingen

-0.14

voÅĻ

-0.14

POSITIVE LOGITS

0.16

iga

0.15

.Enums

0.15

lass

0.14

/vendors

0.14

OA

0.14

olia

0.13

cola

0.13

sta

0.13

oret

0.13

Activations Density 0.084%

parentheses and parenthetical structures

No Comments

No Known Activations