INDEX

Explanations

terms related to compensation and offsets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

-addon

-0.15

lk

-0.15

.Selenium

-0.15

Foreground

-0.14

 Resp

-0.14

wal

-0.14

MLE

-0.14

 Ð¾ÑĩÐµÑĢÐµÐ´

-0.13

oleon

-0.13

CELER

-0.13

POSITIVE LOGITS

 compensation

0.17

 compensate

0.16

 sized

0.15

ably

0.15

-sized

0.15

pit

0.15

balance

0.15

JI

0.15

 Compensation

0.15

ingly

0.14

Activations Density 0.050%

terms related to compensation and offsets

No Comments

No Known Activations