INDEX

Explanations

mathematical expressions and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ort

-0.16

ORIZONTAL

-0.16

CU

-0.16

 indent

-0.15

IQ

-0.14

ensing

-0.14

chaft

-0.14

JsonValue

-0.13

 joint

-0.13

pet

-0.13

POSITIVE LOGITS

jÃŃm

0.16

/Dk

0.14

uld

0.14

ichen

0.14

.mybatisplus

0.14

syscall

0.14

adro

0.14

ãĥ»ãĥ»ãĥ»↵↵

0.14

achen

0.14

 Hooks

0.14

Activations Density 0.411%

mathematical expressions and equations

No Comments

No Known Activations