INDEX

Explanations

names of individuals, likely in an academic or scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

lingen

-0.17

lege

-0.17

REFIX

-0.16

ladu

-0.15

æĹģ

-0.15

isÃŃ

-0.15

----------</

-0.15

æĸ°èģŀ

-0.14

 defaultMessage

-0.14

remium

-0.14

POSITIVE LOGITS

0.16

 Icon

0.14

yme

0.14

 Facilities

0.14

NP

0.14

 Belle

0.14

 Facility

0.14

.a

0.13

achine

0.13

Activations Density 0.067%

names of individuals, likely in an academic or scientific context

No Comments

No Known Activations