INDEX

Explanations

mentions or indications of a specific type of rating system or review score

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

SB

-0.17

ine

-0.17

im

-0.16

aus

-0.15

iv

-0.15

ex

-0.15

ÙĤ

-0.15

IC

-0.15

ibus

-0.14

iyi

-0.14

POSITIVE LOGITS

ateral

0.23

oris

0.22

alu

0.22

ulu

0.20

aments

0.19

erne

0.19

ighth

0.19

anza

0.19

alach

0.18

abeled

0.18

Activations Density 0.138%

mentions or indications of a specific type of rating system or review score

No Comments

No Known Activations