INDEX

Explanations

features and capabilities related to technology and product specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

bove

-0.15

 tÃ¼rlÃ¼

-0.14

uku

-0.14

uther

-0.14

Î¯Î½Î±

-0.13

uar

-0.13

ãİ

-0.13

à¤Ĥà¤ªà¤°

-0.13

ept

-0.13

 Indexed

-0.13

POSITIVE LOGITS

 included

0.70

included

0.58

 INCLUDED

0.54

 Included

0.53

 incorporated

0.50

 built

0.49

Included

0.49

 builtin

0.47

 integrated

0.44

 baked

0.40

Activations Density 0.333%

features and capabilities related to technology and product specifications

No Comments

No Known Activations