INDEX

Explanations

references to companies and their affiliates

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

engo

-0.16

imary

-0.16

Ð»ÐµÐ¼

-0.15

lea

-0.15

arty

-0.15

oda

-0.15

SEA

-0.15

emin

-0.15

achs

-0.15

mach

-0.14

POSITIVE LOGITS

ecer

0.15

 pill

0.15

olio

0.14

EP

0.14

yb

0.14

 Bald

0.14

 Mount

0.14

 fiction

0.14

avor

0.14

acer

0.14

Activations Density 0.053%

references to companies and their affiliates

No Comments

No Known Activations