INDEX

Explanations

measurements and quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

evin

-0.16

 bland

-0.15

criptor

-0.15

/commons

-0.14

quat

-0.14

 Hein

-0.14

ifa

-0.13

persistent

-0.13

rimon

-0.13

POSITIVE LOGITS

swire

0.17

 Signature

0.17

iste

0.16

ysi

0.15

_signature

0.15

andler

0.15

å³

0.14

_SIGNATURE

0.14

endi

0.14

alnÄ±z

0.14

Activations Density 0.086%

measurements and quantities

No Comments

No Known Activations