INDEX

Explanations

prefixes and suffixes indicating negation or restriction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

nio

-0.17

tti

-0.15

eka

-0.14

	ERROR

-0.14

ç©

-0.14

inx

-0.14

eless

-0.14

baz

-0.14

ted

-0.13

 grÃ¡tis

-0.13

POSITIVE LOGITS

adays

0.17

/pre

0.15

bye

0.14

[email

0.14

etheless

0.14

amo

0.14

rais

0.14

enticate

0.13

ARING

0.13

west

0.13

Activations Density 0.146%

prefixes and suffixes indicating negation or restriction

No Comments

No Known Activations