INDEX

Explanations

textual elements related to statistics and numerical data

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Ãºsqueda

-0.17

ato

-0.15

SEC

-0.14

erals

-0.14

SEC

-0.13

_EXPECT

-0.13

pled

-0.13

 dÃ¢n

-0.13

erah

-0.13

edin

-0.13

POSITIVE LOGITS

 slightly

0.20

otton

0.16

 Finger

0.15

opleft

0.15

 finger

0.15

è¿«

0.14

ullo

0.14

Ħ

0.14

 equally

0.14

ungi

0.14

Activations Density 0.081%

textual elements related to statistics and numerical data

No Known Activations