INDEX

Explanations

references to eggs and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

adir

-0.17

æģ¯

-0.16

rof

-0.16

.Interop

-0.15

engu

-0.15

mnop

-0.15

achu

-0.15

UpInside

-0.15

utow

-0.15

idelberg

-0.14

POSITIVE LOGITS

 Counter

0.15

ar

0.15

 Fallon

0.14

 Scar

0.14

 Gree

0.14

iden

0.14

_IPV

0.14

en

0.13

ona

0.13

Activations Density 0.005%

references to eggs and related concepts

No Comments

No Known Activations