INDEX

Explanations

references or citations to related topics or sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

archy

-0.17

itel

-0.15

iben

-0.15

reamble

-0.15

Ø§Ø±Ø´

-0.15

ãĥ«ãĥī

-0.15

usat

-0.14

rias

-0.14

ITHER

-0.14

usercontent

-0.14

POSITIVE LOGITS

0.17

aeda

0.15

onica

0.15

rawer

0.15

¸

0.14

apon

0.14

ment

0.14

 List

0.14

tal

0.14

 redirectTo

0.14

Activations Density 0.010%

references or citations to related topics or sections

No Comments

No Known Activations