INDEX

Explanations

words related to decision-making and evaluation processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ses

-0.19

ermann

-0.18

ilities

-0.16

names

-0.15

Ø§Ø¡

-0.15

athon

-0.15

erman

-0.14

ana

-0.14

enburg

-0.14

 nhau

-0.14

POSITIVE LOGITS

 whether

0.20

Whether

0.16

 Whether

0.15

avaÅŁ

0.14

quential

0.14

ments

0.14

oader

0.14

wart

0.14

whether

0.14

mente

0.14

Activations Density 0.033%

words related to decision-making and evaluation processes

No Comments

No Known Activations