INDEX

Explanations

file paths and directory structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ump

-0.16

finger

-0.15

loe

-0.15

å®ĺç½ĳ

-0.14

 sight

-0.14

 Sight

-0.14

ãĥ«ãĥķ

-0.14

resent

-0.14

inese

-0.14

eye

-0.14

POSITIVE LOGITS

anness

0.15

Facade

0.14

-equiv

0.14

chu

0.14

ÏĥÎ¹

0.14

 Ã¡n

0.14

wheel

0.14

ivent

0.13

ãĥ¬ãĥĥãĥĪ

0.13

Activations Density 0.008%

file paths and directory structures

No Comments

No Known Activations