INDEX

Explanations

terms related to nuclear structures and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Warp

-0.17

pter

-0.15

ãĥ³ãĥĨãĤ£

-0.15

ixels

-0.14

ey

-0.14

afen

-0.14

 Fork

-0.14

onta

-0.14

 ë©´

-0.14

.Rendering

-0.14

POSITIVE LOGITS

 states

0.15

 Grat

0.15

 centrif

0.15

ziej

0.15

 transitions

0.14

Ð¼Ð°Ð·

0.14

parity

0.14

CMS

0.14

 stability

0.14

 radius

0.14

Activations Density 0.001%

terms related to nuclear structures and processes

No Comments

No Known Activations