INDEX

Explanations

mathematical symbols and notations used in equations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

enne

-0.18

raith

-0.16

 Spir

-0.15

 PUSH

-0.15

wers

-0.14

uchos

-0.14

kea

-0.14

çħ¤

-0.14

hek

-0.14

rud

-0.14

POSITIVE LOGITS

emer

0.15

ANCH

0.14

insic

0.14

STANCE

0.14

Bundle

0.13

ÐµÑĢÐ°Ð»ÑĮ

0.13

ÑĨÐ¸Ð½

0.13

roman

0.13

/chart

0.13

Activations Density 0.027%

mathematical symbols and notations used in equations

No Comments

No Known Activations