INDEX

Explanations

concepts related to risk and uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

avra

-0.15

asm

-0.15

Ø°Ùĩ

-0.14

.say

-0.14

_FMT

-0.13

 actually

-0.13

 Cata

-0.13

 Ø§ÙĦØ°Ùĩ

-0.13

ollo

-0.13

 convin

-0.13

POSITIVE LOGITS

 nature

0.29

 inevitable

0.28

 inev

0.26

 unavoidable

0.25

nature

0.23

 unavoid

0.23

 realities

0.23

 Nature

0.23

 reality

0.23

 sometimes

0.22

Activations Density 0.282%

concepts related to risk and uncertainty

No Comments

No Known Activations