INDEX

Explanations

names of brands, organizations, and notable locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ego

-0.15

EST

-0.15

heimer

-0.15

EST

-0.15

.uni

-0.14

meta

-0.14

cery

-0.14

İ

-0.14

ibia

-0.14

ocre

-0.14

POSITIVE LOGITS

boj

0.19

Rut

0.16

boat

0.15

 Pills

0.15

eron

0.14

reten

0.14

aye

0.14

heard

0.13

/Foundation

0.13

kits

0.13

Activations Density 0.020%

names of brands, organizations, and notable locations

No Comments

No Known Activations