INDEX

Explanations

mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Operator

-0.18

Operator

-0.17

col

-0.17

operator

-0.16

 oper

-0.16

 operator

-0.16

Col

-0.15

.Operator

-0.15

bm

-0.15

digital

-0.15

POSITIVE LOGITS

cases

0.21

atrix

0.21

matrix

0.19

build

0.19

rm

0.17

cal

0.17

ataka

0.17

è¾º

0.16

Cases

0.16

ozem

0.16

Activations Density 0.133%

mathematical symbols and notation

No Comments

No Known Activations