INDEX

Explanations

references to a specific professional wrestling term, particularly related to significant achievements in wrestling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Pai

-0.16

 Bers

-0.16

atori

-0.15

sing

-0.15

eren

-0.14

room

-0.14

ÑĢÐ°Ð¶

-0.14

ensibly

-0.14

iams

-0.14

POSITIVE LOGITS

ts

0.24

/qu

0.22

rd

0.20

ty

0.19

uros

0.18

tt

0.18

mania

0.17

licate

0.17

dition

0.17

uple

0.16

Activations Density 0.013%

references to a specific professional wrestling term, particularly related to significant achievements in wrestling

No Comments

No Known Activations