INDEX

Explanations

phrases that introduce or emphasize concepts related to the idea or theme being discussed

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

uese

-0.18

Ø²Ø©

-0.16

 addCriterion

-0.16

Ð²ÑĢÐ¾Ð¿

-0.16

Î¸Î±

-0.15

ìĿµ

-0.15

.CLASS

-0.15

Vtbl

-0.15

_PRIV

-0.14

_CALLBACK

-0.14

POSITIVE LOGITS

 that

0.16

↵

0.15

 Buen

0.15

 ÐŁÑĢÐ¾Ð´

0.15

...

0.15

ion

0.15

 Mass

0.14

 exchange

0.14

Ger

0.14

 upstream

0.14

Activations Density 0.100%

phrases that introduce or emphasize concepts related to the idea or theme being discussed

No Comments

No Known Activations