INDEX

Explanations

references to rivers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ALAR

-0.16

-valu

-0.15

utch

-0.15

Zur

-0.15

ÂŃi

-0.14

hra

-0.14

alus

-0.14

POSITIVE LOGITS

idal

0.17

erras

0.16

iano

0.16

å»³

0.15

 bend

0.15

ÐºÐ°Ð²

0.15

kdir

0.15

åİħ

0.14

ubits

0.14

mand

0.14

Activations Density 0.004%

references to rivers

No Comments

No Known Activations