INDEX

Explanations

numerical data and statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ikes

-0.15

oft

-0.14

bread

-0.14

 nhiÃªn

-0.13

LAS

-0.13

ults

-0.13

utra

-0.13

Ĩ

-0.13

ayas

-0.13

 Ä°Ã§

-0.13

POSITIVE LOGITS

oÅĻ

0.16

weg

0.15

IGHL

0.15

 TORT

0.14

omo

0.14

ptune

0.14

rey

0.14

.writeln

0.13

eliac

0.13

Activations Density 0.157%

numerical data and statistical information

No Comments

No Known Activations