INDEX

Explanations

concepts related to problems, solutions, and resolutions 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ucid

-0.15

ComputedStyle

-0.15

apon

-0.15

 proverb

-0.15

 hence

-0.14

hopefully

-0.14

ÐµÑĢÐµ

-0.14

á»©

-0.14

ensex

-0.14

.getTag

-0.13

POSITIVE LOGITS

 actually

0.28

actually

0.21

 Actually

0.19

Actually

0.19

 actual

0.18

 quite

0.18

 nice

0.18

Interestingly

0.17

 clever

0.17

 wikipedia

0.17

Activations Density 0.035%

concepts related to problems, solutions, and resolutions in various contexts

No Comments

No Known Activations