INDEX

Explanations

words indicating presence in challenging or critical situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ilage

-0.16

å¯¿

-0.16

iber

-0.16

/GPL

-0.15

Ø§Ø¯Ùħ

-0.15

ibern

-0.15

 devant

-0.14

-regexp

-0.13

ederland

-0.13

Ð½Ð¾Ð·

-0.13

POSITIVE LOGITS

ror

0.15

abus

0.15

ness

0.14

otto

0.14

foot

0.14

aben

0.14

rene

0.14

agh

0.14

agate

0.13

abella

0.13

Activations Density 0.009%

words indicating presence in challenging or critical situations

No Comments

No Known Activations