INDEX

Explanations

phrases indicating personal experiences and emotions related to participation in events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

outh

-0.14

ê¸ī

-0.13

ilight

-0.13

akedown

-0.13

sworth

-0.13

_UINT

-0.13

[color

-0.13

 Vendor

-0.13

resher

-0.13

lider

-0.13

POSITIVE LOGITS

HostName

0.17

 Patreon

0.14

kin

0.14

experimental

0.14

SizeMode

0.13

bern

0.13

ìĥģìĿĦ

0.13

acha

0.13

 Ð·Ð°Ð»

0.13

ç´

0.13

Activations Density 0.002%

phrases indicating personal experiences and emotions related to participation in events

No Comments

No Known Activations