INDEX

Explanations

references to sources and citations in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.16

er

-0.15

arat

-0.15

 Samar

-0.15

ihn

-0.15

ossa

-0.15

 Amir

-0.14

zee

-0.14

abr

-0.14

Pop

-0.14

POSITIVE LOGITS

Ã´i

0.17

 ÎµÎ¼ÏĢ

0.16

uibModal

0.15

 meiden

0.15

hv

0.15

uren

0.14

ìłł

0.14

hausen

0.14

.bytes

0.13

koli

0.13

Activations Density 0.124%

references to sources and citations in text

No Comments

No Known Activations