INDEX

Explanations

quotes or measurements related to dimensions and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ellen

-0.17

aran

-0.16

TON

-0.16

stad

-0.15

/gin

-0.14

Zem

-0.14

 Tone

-0.14

dge

-0.14

je

-0.14

dire

-0.14

POSITIVE LOGITS

-wide

0.24

-long

0.21

wide

0.20

 diameter

0.20

-radius

0.19

 wide

0.18

itzer

0.18

 radius

0.17

-high

0.17

maid

0.16

Activations Density 0.047%

quotes or measurements related to dimensions and specifications

No Comments

No Known Activations