INDEX

Explanations

references to specific organizations, certifications, or programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ult

-0.19

Facade

-0.15

cobra

-0.15

ÏĦÎ¹Î½

-0.15

enheim

-0.15

ed

-0.15

ute

-0.15

orce

-0.14

amera

-0.14

.synthetic

-0.14

POSITIVE LOGITS

iddy

0.17

ieber

0.17

ee

0.16

acom

0.15

=count

0.15

zens

0.15

APTER

0.15

 Cone

0.14

acro

0.14

nob

0.14

Activations Density 0.059%

references to specific organizations, certifications, or programs

No Comments

No Known Activations