INDEX

Explanations

references to "hall" 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

itel

-0.17

yk

-0.16

htdocs

-0.16

ext

-0.16

ancies

-0.16

elle

-0.16

emo

-0.16

Î¼ÏĢÎ¿

-0.15

ãĥ¼

-0.15

ovich

-0.15

POSITIVE LOGITS

marks

0.36

iday

0.34

ways

0.29

oran

0.28

ibur

0.27

ows

0.26

mark

0.26

statt

0.25

ifax

0.25

marked

0.23

Activations Density 0.015%

references to "hall" in various contexts

No Comments

No Known Activations