INDEX

Explanations

words and phrases that evoke positive emotions or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

orny

-0.16

uchen

-0.16

å½

-0.15

zee

-0.15

ëĭī

-0.14

Ø§Ø

-0.14

ober

-0.14

.Head

-0.14

oke

-0.14

[email

-0.14

POSITIVE LOGITS

zas

0.17

/conf

0.15

rollo

0.14

unic

0.14

Egg

0.14

aras

0.13

_busy

0.13

ibi

0.13

Gib

0.13

Activations Density 0.716%

words and phrases that evoke positive emotions or experiences

No Comments

No Known Activations