INDEX

Explanations

instances of mathematical expressions or symbols related to scientific models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÑĩÐ¸Ð»

-0.17

umat

-0.16

elmet

-0.15

 Feinstein

-0.15

ako

-0.15

ÑĤÐ°Ð»

-0.14

woke

-0.14

 æ»

-0.14

usa

-0.14

sing

-0.14

POSITIVE LOGITS

ÂĢÂĻ

0.15

igator

0.14

'Brien

0.14

EDIUM

0.14

_sold

0.14

eh

0.14

*@

0.14

Ø¸ÙħØ©

0.14

ucursal

0.14

icha

0.13

Activations Density 0.007%

instances of mathematical expressions or symbols related to scientific models

No Comments

No Known Activations