INDEX

Explanations

locations or addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

salt

-0.16

chwitz

-0.15

erea

-0.15

vale

-0.14

oyer

-0.14

MethodManager

-0.14

 McCart

-0.14

yc

-0.14

avia

-0.14

hc

-0.14

POSITIVE LOGITS

ctic

0.15

Ø¯Ø§Ùħ

0.15

PIE

0.15

 Dual

0.14

pun

0.14

eced

0.14

Dual

0.14

Pie

0.14

ãĥ¼ãĥĦ

0.14

dam

0.14

Activations Density 0.047%

locations or addresses

No Comments

No Known Activations