INDEX

Explanations

punctuation marks, particularly commas, in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÑĢÐ¸Ñĩ

-0.16

odesk

-0.15

edii

-0.14

zenie

-0.14

urity

-0.14

ujemy

-0.14

kul

-0.14

itzer

-0.13

ProcessEvent

-0.13

CellStyle

-0.13

POSITIVE LOGITS

Ã¡d

0.15

terrain

0.15

ampaign

0.15

èħ°

0.14

 Kenny

0.14

Ing

0.13

iffer

0.13

(CL

0.13

pecially

0.13

umo

0.13

Activations Density 0.063%

punctuation marks, particularly commas, in various contexts

No Comments

No Known Activations