INDEX

Explanations

references to institutions or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ebe

-0.17

.onView

-0.16

Ñľ

-0.15

chemas

-0.14

 Wich

-0.14

eki

-0.13

tes

-0.13

 Elekt

-0.13

 (*((

-0.13

otch

-0.13

POSITIVE LOGITS

aggable

0.16

 presence

0.14

LocalizedString

0.14

ÄĻd

0.14

Roy

0.14

 Super

0.14

0.13

ivant

0.13

Roy

0.13

urg

0.13

Activations Density 0.326%

references to institutions or organizations

No Comments

No Known Activations