INDEX

Explanations

references to assistance or support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Neill

-0.16

ÙĨÙħ

-0.15

NavBar

-0.15

ichni

-0.14

Nic

-0.14

orz

-0.14

nez

-0.14

stile

-0.14

NotificationCenter

-0.14

odate

-0.13

POSITIVE LOGITS

1.13

0.78

ÂłN

0.60

 ÙĨ

0.56

_n

0.54

=N

0.54

.N

0.49

 ÐĿ

0.48

.n

0.48

Activations Density 0.213%

references to assistance or support

No Comments

No Known Activations