INDEX

Explanations

instances of the word "charge" and its forms related to financial transactions or fees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 çĿ

-0.15

ski

-0.15

mars

-0.14

reme

-0.14

eme

-0.14

iggins

-0.14

jamin

-0.14

ja

-0.14

ention

-0.14

server

-0.14

POSITIVE LOGITS

edly

0.20

edImage

0.17

able

0.17

buie

0.17

.$.

0.16

illac

0.16

ful

0.16

ments

0.15

hold

0.15

yonel

0.15

Activations Density 0.037%

instances of the word "charge" and its forms related to financial transactions or fees

No Comments

No Known Activations