INDEX

Explanations

attributes and specifications related to book formats and condition details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Ð»Ð¸ÑĪÐºÐ¾Ð¼

-0.15

ÑĢÑĥÐ½

-0.15

TG

-0.15

ixon

-0.14

 backgroundImage

-0.14

readcr

-0.14

 features

-0.14

Wes

-0.14

 overd

-0.14

SE

-0.13

POSITIVE LOGITS

lÃ¼

0.17

avad

0.16

_inches

0.14

ÏģÏİÎ½

0.14

ristol

0.14

 Ø·ÙĦ

0.14

_unset

0.14

èŀ

0.14

oons

0.14

ãĤµãĤ¤ãĤº

0.14

Activations Density 0.016%

attributes and specifications related to book formats and condition details

No Comments

No Known Activations