INDEX

Explanations

instances of the word "use" 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ova

-0.18

ooks

-0.17

posit

-0.15

onation

-0.15

ional

-0.14

keley

-0.14

appy

-0.14

culus

-0.14

Defaults

-0.14

 Transportation

-0.13

POSITIVE LOGITS

sville

0.17

aint

0.16

alic

0.16

ection

0.15

lesi

0.15

 Levine

0.15

_common

0.14

oÄŁunluk

0.14

 Variable

0.14

 COMMON

0.14

Activations Density 0.012%

instances of the word "use" in various contexts

No Comments

No Known Activations