INDEX

Explanations

instances of reporting or communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

innamon

-0.16

fel

-0.15

ãĥĥãĥĦ

-0.15

PIC

-0.15

 contr

-0.14

zes

-0.14

ies

-0.14

ourmet

-0.14

PIC

-0.14

aram

-0.14

POSITIVE LOGITS

esson

0.19

aÅĻ

0.17

poon

0.17

 Hanging

0.16

Ã¤l

0.15

ocu

0.15

 Tradable

0.15

us

0.14

agus

0.14

Yug

0.14

Activations Density 0.040%

instances of reporting or communication

No Comments

No Known Activations