INDEX

Explanations

names of authors and publishers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

podob

-0.14

Ã¼rn

-0.14

anja

-0.13

abbo

-0.13

 Bryce

-0.13

ilight

-0.13

(Event

-0.13

 showError

-0.12

à¸´

-0.12

(Editor

-0.12

POSITIVE LOGITS

Ã©

0.46

Äĵ

0.44

Ã«

0.42

ec

0.39

ãģĪ

0.39

Ã¨

0.39

ew

0.39

Ãª

0.38

Ðµ

0.37

0.36

Activations Density 0.243%

names of authors and publishers

No Comments

No Known Activations