INDEX

Explanations

references to geographical locations or mapping information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

aul

-0.17

sil

-0.17

aring

-0.16

/she

-0.15

ree

-0.15

AEA

-0.14

rena

-0.14

APT

-0.14

ux

-0.14

ards

-0.14

POSITIVE LOGITS

ephir

0.18

orrent

0.16

aldo

0.14

LLU

0.14

lights

0.14

itori

0.13

kad

0.13

herent

0.13

ControlItem

0.13

iday

0.13

Activations Density 0.039%

references to geographical locations or mapping information

No Comments

No Known Activations