INDEX

Explanations

punctuation marks, particularly colons and periods, indicating structural elements of the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Ù¾Ø§ÛĮ

-0.15

ÑĤÐ¾Ð½

-0.15

.TestTools

-0.14

McL

-0.14

ÏĦÎµÏį

-0.14

ÐµÐ³ÑĢÐ°

-0.14

ÐµÐºÑĥ

-0.14

à¸¥à¸³

-0.14

çª

-0.14

amba

-0.14

POSITIVE LOGITS

quote

0.16

wr

0.14

Ø²Ùĩ

0.14

ovit

0.14

QUOTE

0.14

Dix

0.14

 Typed

0.14

rete

0.14

Activations Density 0.036%

punctuation marks, particularly colons and periods, indicating structural elements of the text

No Comments

No Known Activations