INDEX

Explanations

references to media coverage and narratives surrounding historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

_INCREMENT

-0.16

atron

-0.15

Ð¾ÑĤÐ¾Ð²

-0.14

yem

-0.14

 soundtrack

-0.14

 weblog

-0.14

 vidÃ©os

-0.14

Ð¾Ð·Ð¸

-0.14

rze

-0.14

Draft

-0.14

POSITIVE LOGITS

 serialized

0.24

 serialization

0.23

 Punch

0.23

 dime

0.23

Serialized

0.21

 serial

0.21

serialized

0.21

 Serialization

0.20

 magazine

0.19

 Weekly

0.19

Activations Density 0.070%

references to media coverage and narratives surrounding historical events

No Comments

No Known Activations