INDEX

Explanations

incidents or references related to notable events or mentions of certain topics

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

Not in Any Lists

No Comments

Negative Logits

orus

-0.17

vation

-0.16

izin

-0.14

 ucwords

-0.14

inity

-0.14

hs

-0.14

GLOBALS

-0.14

 Fluent

-0.13

reator

-0.13

oon

-0.13

POSITIVE LOGITS

oux

0.18

AndView

0.18

imei

0.18

acre

0.17

thora

0.17

eker

0.15

deaux

0.15

ÂłÂł

0.15

ekli

0.15

ovna

0.15

Activations Density 0.012%

incidents or references related to notable events or mentions of certain topics

No Comments

No Known Activations