INDEX

Explanations

terms and phrases related to game mechanics and system functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.15

ÙĪØ²ÛĮ

-0.15

anyl

-0.14

reak

-0.14

 Strauss

-0.13

ledged

-0.13

-IS

-0.13

ep

-0.13

embedding

-0.13

sei

-0.13

POSITIVE LOGITS

 maybe

0.16

_INLINE

0.15

@brief

0.15

èľ

0.15

 perhaps

0.14

aybe

0.14

ptron

0.14

Invoker

0.14

 pronounce

0.14

Î¿

0.14

Activations Density 0.079%

terms and phrases related to game mechanics and system functionality

No Comments

No Known Activations