INDEX

Explanations

phrases indicating inclusivity or belonging to a group

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

è³¢

-0.16

rador

-0.15

 ÙĦÛĮÚ¯

-0.15

 fists

-0.14

Ã©ri

-0.14

ovie

-0.14

ÐłÐĿ

-0.14

ottage

-0.14

ayer

-0.13

autos

-0.13

POSITIVE LOGITS

.scalablytyped

0.18

ahi

0.16

 Essays

0.15

eness

0.14

BackStack

0.14

frag

0.14

jl

0.13

åļ

0.13

esen

0.13

roid

0.13

Activations Density 0.028%

phrases indicating inclusivity or belonging to a group

No Comments

No Known Activations