INDEX

Explanations

mathematical symbols and notations related to equations

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

 varargin

-0.15

riba

-0.14

ahn

-0.14

zig

-0.14

Ð°ÑĢÐ°ÑĤ

-0.14

 DeepCopy

-0.14

 ngang

-0.14

achu

-0.14

.parallel

-0.13

alue

-0.13

POSITIVE LOGITS

 @{↵

0.17

Canceled

0.15

ivr

0.14

vÄĽ

0.14

bon

0.14

 Rupert

0.13

lahoma

0.13

 recogn

0.13

 Bulletin

0.13

ouri

0.13

Activations Density 0.044%

mathematical symbols and notations related to equations

No Comments

No Known Activations