INDEX

Explanations

names and their associated details, specifically in a structured format such as lists or tables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

enek

-0.16

bjerg

-0.16

uisse

-0.16

anship

-0.14

elves

-0.14

plorer

-0.14

sworth

-0.14

parator

-0.14

 hitch

-0.14

asin

-0.14

POSITIVE LOGITS

Å¯r

0.15

ÎµÎ¯

0.14

Ã²i

0.14

 Sullivan

0.14

 disfr

0.14

 Scre

0.14

ÑĥÑĩÐ°

0.13

cher

0.13

 Savage

0.13

Activations Density 0.185%

names and their associated details, specifically in a structured format such as lists or tables

No Comments

No Known Activations