INDEX

Explanations

the word "for" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

steller

-0.17

ignet

-0.16

ÑĥÐ²

-0.15

ÑĨÐ¸Ðº

-0.15

rega

-0.14

vat

-0.14

wers

-0.14

antino

-0.13

 Abstract

-0.13

.Abstract

-0.13

POSITIVE LOGITS

otten

0.16

bery

0.15

 ÙĨÛĮ

0.14

 Heller

0.13

esome

0.13

ded

0.13

ripper

0.13

ugs

0.13

ìĸ´

0.12

/of

0.12

Activations Density 0.161%

the word "for" in various contexts

No Comments

No Known Activations