INDEX

Explanations

numerical values or statistics related to specific measurements and data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 çĿ

-0.16

İ

-0.14

 eskort

-0.14

erap

-0.13

resi

-0.13

íħľ

-0.13

.Orientation

-0.13

elik

-0.13

 Hell

-0.13

 mutual

-0.13

POSITIVE LOGITS

ossal

0.15

ãĥ«ãĤ¯

0.15

jong

0.15

ToProps

0.15

ãĥªãĤ¢

0.14

elm

0.14

fld

0.14

CPR

0.14

ÐµÐ»Ð°

0.14

nect

0.13

Activations Density 0.209%

numerical values or statistics related to specific measurements and data

No Comments

No Known Activations