INDEX

Explanations

negative phrases or expressions indicating doubt or lack of certainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

reen

-0.15

 ìķĦëĭĪëĿ¼

-0.14

 horribly

-0.14

å¹¶ä¸į

-0.14

avin

-0.14

olini

-0.13

ouv

-0.13

 nonzero

-0.13

inia

-0.13

 somehow

-0.13

POSITIVE LOGITS

any

0.25

 anymore

0.24

 spared

0.19

 much

0.19

Any

0.18

Any

0.18

 less

0.18

 anyhow

0.18

any

0.18

 anybody

0.17

Activations Density 0.221%

negative phrases or expressions indicating doubt or lack of certainty

No Comments

No Known Activations