INDEX

Explanations

references to the Strait of Hormuz

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Brook

-0.16

chalk

-0.15

chief

-0.15

alue

-0.14

Î´Î¬

-0.14

ÏĨÏħ

-0.14

aram

-0.14

Vu

-0.14

agna

-0.14

styl

-0.14

POSITIVE LOGITS

zeitig

0.15

CCA

0.15

tees

0.15

loh

0.14

Ð¬

0.14

gow

0.14

otto

0.14

essel

0.14

/XML

0.14

rott

0.14

Activations Density 0.003%

references to the Strait of Hormuz

No Comments

No Known Activations