INDEX

Explanations

negative sentiments or stances regarding community and health topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

hog

-0.17

ansi

-0.16

avin

-0.16

ahoo

-0.15

 bang

-0.14

 Doll

-0.14

adows

-0.14

é«

-0.14

èº

-0.14

 seins

-0.14

POSITIVE LOGITS

lander

0.14

ompiler

0.14

 Burton

0.14

(Column

0.13

ibur

0.13

Abr

0.13

 Maver

0.13

zik

0.13

åł

0.13

unkt

0.13

Activations Density 0.147%

negative sentiments or stances regarding community and health topics

No Comments

No Known Activations