INDEX

Explanations

phrases indicating necessity or the concept of "need."

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

eltas

-0.19

 Swords

-0.15

IFT

-0.15

raid

-0.15

PRS

-0.14

duct

-0.14

nage

-0.14

å³

-0.14

ileo

-0.14

 lazy

-0.13

POSITIVE LOGITS

olan

0.15

ayout

0.15

ereal

0.15

ÑĢÐ¾Ñĩ

0.15

ä»ĭ

0.14

upt

0.14

Lun

0.14

ema

0.14

 gere

0.14

iger

0.14

Activations Density 0.032%

phrases indicating necessity or the concept of "need."

No Comments

No Known Activations