INDEX

Explanations

repeated numerical codes related to software versions or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ing

-0.16

ontent

-0.15

onth

-0.15

itis

-0.14

inged

-0.14

gabe

-0.14

lient

-0.14

lamaz

-0.14

afen

-0.14

inging

-0.14

POSITIVE LOGITS

uong

0.19

.Singleton

0.16

.alloc

0.15

ÐµÐ²Ð¾

0.15

uger

0.15

_singleton

0.14

umin

0.14

ADIUS

0.14

RULE

0.14

adium

0.14

Activations Density 0.007%

repeated numerical codes related to software versions or systems

No Comments

No Known Activations