INDEX

Explanations

phrases related to adaptation and adjusting to new situations

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

.mapping

-0.17

hma

-0.16

inia

-0.16

ndo

-0.16

xit

-0.15

ernals

-0.14

gency

-0.14

lette

-0.14

Utility

-0.14

ogany

-0.14

POSITIVE LOGITS

ably

0.16

habit

0.15

czy

0.13

 habit

0.13

 adjusts

0.13

adjust

0.13

fov

0.13

 change

0.13

eras

0.13

 Serializable

0.13

Activations Density 0.086%

phrases related to adaptation and adjusting to new situations

No Comments

No Known Activations