INDEX

Explanations

quantitative measurements and numerical representations in various contexts

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

enco

-0.16

oup

-0.15

RowAt

-0.14

 Hemp

-0.14

_signed

-0.14

Ø§ÙģÛĮ

-0.14

.rc

-0.14

_initializer

-0.14

POSITIVE LOGITS

enie

0.15

ÙĬÙĨÙĩ

0.14

åı¸

0.14

 McGr

0.14

umo

0.13

hou

0.13

 Olsen

0.13

//{{

0.13

 feeder

0.13

ziel

0.13

Activations Density 0.028%

quantitative measurements and numerical representations in various contexts

No Comments

No Known Activations