INDEX

Explanations

occurrences of mathematical symbols and formatting elements that indicate mathematical notation

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

eva

-0.16

rou

-0.16

horia

-0.16

oser

-0.15

quip

-0.15

 abstract

-0.15

Sharp

-0.14

ä¾

-0.14

tip

-0.14

 Lars

-0.14

POSITIVE LOGITS

imes

0.37

extr

0.23

entimes

0.20

 times

0.20

anh

0.18

imest

0.18

_times

0.17

ies

0.17

ims

0.16

ines

0.16

Activations Density 0.007%

occurrences of mathematical symbols and formatting elements that indicate mathematical notation

No Comments

No Known Activations