INDEX

Explanations

phrases related to relationships and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

?url

-0.18

agara

-0.14

cci

-0.14

inee

-0.14

ataka

-0.14

abox

-0.13

fell

-0.13

Î¹ÎºÎ±

-0.13

Illegal

-0.13

ÐµÑģÑı

-0.13

POSITIVE LOGITS

anko

0.16

udd

0.16

dash

0.15

odor

0.14

ç¦

0.13

.hash

0.13

 Hein

0.13

CX

0.13

iad

0.13

UIG

0.13

Activations Density 0.241%

phrases related to relationships and connections

No Comments

No Known Activations