INDEX

Explanations

phrases that express uncertainty or inquiry about knowledge and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ph

-0.15

igt

-0.15

els

-0.14

 Tomorrow

-0.14

phin

-0.14

rello

-0.14

å½¹

-0.14

Į

-0.14

alu

-0.13

_gps

-0.13

POSITIVE LOGITS

Ã¡li

0.16

OLOR

0.15

.gov

0.15

&&!

0.15

Subscriber

0.14

omidou

0.14

.norm

0.14

anch

0.14

aca

0.14

ahas

0.14

Activations Density 0.123%

phrases that express uncertainty or inquiry about knowledge and understanding

No Comments

No Known Activations