INDEX

Explanations

numerical values and quantities related to various contexts

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

 Wealth

-0.15

 wealth

-0.15

PermissionsResult

-0.15

/copyleft

-0.15

à¸±à¹Ī

-0.14

sher

-0.14

 Ð´Ð¾Ð»Ð¶

-0.13

phas

-0.13

 ward

-0.13

POSITIVE LOGITS

0.16

ó

0.15

defer

0.14

ãĥ³ãĥĪ

0.14

iami

0.14

iddles

0.14

Ã¤ft

0.14

plitude

0.14

 inferior

0.14

Activations Density 0.055%

numerical values and quantities related to various contexts

No Comments

No Known Activations