INDEX

Explanations

phrases indicating cooperation or collaboration

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

apis

-0.17

antino

-0.14

.yy

-0.14

displayName

-0.14

è²´

-0.14

legt

-0.14

endra

-0.13

inae

-0.13

ALSE

-0.13

inner

-0.13

POSITIVE LOGITS

 approach

0.17

 regard

0.17

cken

0.16

Choice

0.16

 ability

0.15

utenberg

0.15

 choice

0.15

 intent

0.15

 regards

0.15

readcr

0.14

Activations Density 0.085%

phrases indicating cooperation or collaboration

No Comments

No Known Activations