INDEX

Explanations

references or citations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

nÄĽm

-0.15

kÃ¡m

-0.15

auf

-0.15

 Carrier

-0.14

 carriers

-0.14

Ã´i

-0.14

 Bitte

-0.14

idges

-0.14

ellan

-0.14

 carrier

-0.14

POSITIVE LOGITS

elo

0.15

ysl

0.15

.sourceforge

0.15

ãĤ¤ãĥī

0.15

 overd

0.14

Kop

0.14

Spo

0.14

.sf

0.14

OSH

0.14

Slo

0.13

Activations Density 0.000%

references or citations within the text

No Comments

No Known Activations