INDEX

Explanations

references to newsletters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ifton

-0.16

 chairman

-0.15

/cms

-0.14

hoa

-0.14

View

-0.14

urga

-0.14

ç£

-0.14

isme

-0.13

aset

-0.13

 Chairman

-0.13

POSITIVE LOGITS

ÙĪØ²ÛĮ

0.15

re

0.15

baum

0.15

_strategy

0.14

."↵↵↵↵

0.14

 Gore

0.14

yne

0.14

ÑĢÐ°Ð¹

0.14

reuse

0.14

oyer

0.13

Activations Density 0.002%

references to newsletters

No Comments

No Known Activations