INDEX

Explanations

numerical data and statistics related to various comparisons or results

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

asher

-0.16

.bz

-0.15

.hs

-0.15

stry

-0.15

getto

-0.15

ÐºÐ°Ñģ

-0.14

 lady

-0.14

à¸¶à¸ĩ

-0.14

quan

-0.14

onis

-0.14

POSITIVE LOGITS

xad

0.15

.BorderColor

0.15

olen

0.14

onders

0.14

<![

0.14

erture

0.14

ÙİØ£

0.14

ADX

0.13

Å¡ak

0.13

assadors

0.13

Activations Density 0.159%

numerical data and statistics related to various comparisons or results

No Comments

No Known Activations