INDEX

Explanations

sentiment-related phrases indicating mixed or varied responses and opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÏĥÏĦÎµ

-0.15

 Punch

-0.15

imei

-0.14

loc

-0.14

 punch

-0.13

 kter

-0.13

rix

-0.13

lla

-0.13

POSITIVE LOGITS

 depending

0.26

depending

0.22

 Depending

0.19

aghetti

0.18

Depending

0.17

depends

0.16

fragistics

0.16

 tÃ¹y

0.15

 Depends

0.15

indir

0.15

Activations Density 0.103%

sentiment-related phrases indicating mixed or varied responses and opinions

No Comments

No Known Activations