INDEX

Explanations

references to awards and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

amage

-0.14

astics

-0.14

illon

-0.14

edor

-0.14

affiliate

-0.14

_ASSUME

-0.14

 erfolgre

-0.14

utter

-0.14

ç±į

-0.13

realloc

-0.13

POSITIVE LOGITS

 honorable

0.29

 runner

0.26

 Runner

0.25

 runners

0.24

runner

0.23

 Overall

0.23

 Audience

0.22

Hon

0.21

Runner

0.20

 Mention

0.20

Activations Density 0.051%

references to awards and achievements

No Comments

No Known Activations