INDEX

Explanations

negations and qualifiers that express doubt or constraints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

avin

-0.18

itti

-0.17

pons

-0.15

acht

-0.15

haf

-0.15

 terribly

-0.14

 nonzero

-0.14

äºİæĺ¯

-0.14

isha

-0.14

POSITIVE LOGITS

 anymore

0.23

any

0.23

ä»»ä½ķ

0.22

any

0.21

Any

0.19

Any

0.19

 neither

0.19

.createObject

0.18

 qualquer

0.18

_any

0.16

Activations Density 0.393%

negations and qualifiers that express doubt or constraints

No Comments

No Known Activations