INDEX

Explanations

terms related to professional roles and expertise in various industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

stamp

-0.15

AMA

-0.15

 Enumeration

-0.14

ampie

-0.14

neau

-0.14

Ð±Ð°Ñĩ

-0.14

iben

-0.13

ÑĨÐ¸ÑĤ

-0.13

ibel

-0.13

baugh

-0.13

POSITIVE LOGITS

Ä±ÅŁÄ±k

0.15

who

0.15

 Granite

0.15

umm

0.14

imal

0.14

omatic

0.14

:Register

0.14

 overcoming

0.13

vw

0.13

Activations Density 0.106%

terms related to professional roles and expertise in various industries

No Comments

No Known Activations