INDEX

Explanations

verbs related to actions, achievements, and experiences in professional and educational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÑĪÐºÐ°

-0.17

issan

-0.17

-0.15

.Magenta

-0.15

arra

-0.14

verture

-0.14

 Signed

-0.14

orsi

-0.13

Signed

-0.13

ä¸ĺ

-0.13

POSITIVE LOGITS

clid

0.17

 prev

0.16

ext

0.15

.um

0.15

kes

0.14

eph

0.14

-ext

0.14

Å¾it

0.14

 lect

0.14

 createSelector

0.13

Activations Density 0.063%

verbs related to actions, achievements, and experiences in professional and educational contexts

No Comments

No Known Activations