INDEX

Explanations

occurrences of the word "all" 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

icum

-0.16

 ç¨

-0.14

.setter

-0.14

ogi

-0.14

edback

-0.14

éĳĳ

-0.14

icky

-0.13

icz

-0.13

 Balk

-0.13

POSITIVE LOGITS

geme

0.20

igator

0.20

iances

0.16

resco

0.16

LLLL

0.15

ERGY

0.15

uzione

0.14

ustr

0.14

fre

0.14

winner

0.14

Activations Density 0.198%

occurrences of the word "all" in various contexts

No Comments

No Known Activations