INDEX

Explanations

phrases expressing desire or preference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Dub

-0.16

 ries

-0.15

AKE

-0.15

 over

-0.14

ARDS

-0.14

ubu

-0.14

refixer

-0.13

 åĳ

-0.13

PLE

-0.13

uer

-0.13

POSITIVE LOGITS

onia

0.14

oha

0.14

ÙİØ£

0.14

aliz

0.14

ÙĴØ³

0.14

iti

0.13

íĴĪ

0.13

ÏĩÏİ

0.13

erus

0.13

omatic

0.13

Activations Density 0.016%

phrases expressing desire or preference

No Comments

No Known Activations