INDEX

Explanations

phrases that indicate evaluation or judgment about actions and behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ãĥ³ãĥ

-0.15

erli

-0.15

 Various

-0.14

yer

-0.14

pard

-0.14

Ã§Ä±

-0.14

bits

-0.13

stery

-0.13

 ÐĿÑĥ

-0.13

POSITIVE LOGITS

ing

0.17

 pure

0.16

 sorts

0.16

antry

0.16

 engineering

0.16

 twentieth

0.15

 proportions

0.15

art

0.15

 ekip

0.14

 brink

0.14

Activations Density 0.195%

phrases that indicate evaluation or judgment about actions and behaviors

No Comments

No Known Activations

phrases that indicate evaluation or judgment about actions and behaviors

No Comments

No Known Activations