INDEX

Explanations

mentions of geographical locations, particularly those starting with "Ky"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

chip

-0.17

onica

-0.15

.EXTRA

-0.15

apur

-0.15

èĶµ

-0.15

erties

-0.14

Ĩ

-0.14

acades

-0.14

 vals

-0.14

inery

-0.14

POSITIVE LOGITS

rgyz

0.26

Ky

0.20

rie

0.19

oto

0.17

ameleon

0.17

riad

0.17

OTO

0.17

ky

0.17

Ky

0.16

ung

0.16

Activations Density 0.006%

mentions of geographical locations, particularly those starting with "Ky"

No Comments

No Known Activations