INDEX

Explanations

punctuation marks, specifically single and double quotation marks, and semicolons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oper

-0.17

 pure

-0.17

sip

-0.16

Ð¾ÑĤÐ°

-0.15

 merchant

-0.14

chg

-0.14

tr

-0.14

her

-0.14

 Programming

-0.14

udes

-0.14

POSITIVE LOGITS

eya

0.14

stamp

0.14

iones

0.14

Ãłu

0.14

 COMMON

0.14

ãĤ¶

0.14

azzo

0.14

cente

0.13

endir

0.13

PK

0.13

Activations Density 0.004%

punctuation marks, specifically single and double quotation marks, and semicolons

No Comments

No Known Activations