INDEX

Explanations

sentences involving expressing opinions, reactions, or critiques

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

vid

-0.17

ire

-0.15

Ð²Ð¸Ð´

-0.14

Vid

-0.14

PTS

-0.14

pil

-0.14

elda

-0.14

PT

-0.14

 others

-0.13

osh

-0.13

POSITIVE LOGITS

Ã½t

0.16

iscrimination

0.16

iciary

0.16

_HERE

0.16

 PROFITS

0.15

,application

0.14

ioned

0.14

mpar

0.14

]={↵

0.14

.sg

0.14

Activations Density 0.395%

sentences involving expressing opinions, reactions, or critiques

No Comments

No Known Activations