INDEX

Explanations

references to "Wall Street Journal."

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

anmar

-0.15

cale

-0.15

orm

-0.14

Ã®tre

-0.14

thon

-0.14

emon

-0.14

uku

-0.14

ity

-0.14

iping

-0.13

ÙĤØ¯

-0.13

POSITIVE LOGITS

 Journal

0.44

Journal

0.37

 journal

0.36

_journal

0.30

journal

0.26

ournal

0.25

OURNAL

0.24

 journals

0.23

 Transcript

0.18

ournals

0.17

Activations Density 0.004%

references to "Wall Street Journal."

No Comments

No Known Activations