INDEX

Explanations

mathematical symbols and variables common in equations and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.ta

-0.15

bpp

-0.15

fkk

-0.15

onis

-0.14

é¦Ĩ

-0.14

azz

-0.14

 Cynthia

-0.14

.chapter

-0.13

cu

-0.13

lap

-0.13

POSITIVE LOGITS

panic

0.17

ÐºÐ¾Ð´

0.16

BILE

0.15

ToSend

0.13

obile

0.13

ahl

0.13

ÑĨÑĮ

0.13

gable

0.13

 sublicense

0.13

Ticks

0.13

Activations Density 0.602%

mathematical symbols and variables common in equations and expressions

No Comments

No Known Activations