INDEX

Explanations

terms related to acceleration and speed in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 UNITY

-0.15

åĳ

-0.14

ession

-0.14

ìĹŃ

-0.13

ild

-0.13

elt

-0.13

éľĩ

-0.13

lake

-0.13

.Unity

-0.13

 cref

-0.13

POSITIVE LOGITS

 pace

0.15

 paced

0.15

asa

0.15

/power

0.15

©

0.14

ouncil

0.14

substr

0.14

 toward

0.14

ubar

0.14

/de

0.13

Activations Density 0.049%

terms related to acceleration and speed in various contexts

No Comments

No Known Activations