INDEX

Explanations

terms related to fixed characteristics or parameters in a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

urch

-0.18

lem

-0.17

cak

-0.16

erp

-0.15

kla

-0.15

rong

-0.15

iku

-0.15

ç»Ł

-0.15

onne

-0.14

/epl

-0.14

POSITIVE LOGITS

/static

0.22

-fixed

0.20

-rate

0.18

/random

0.18

-width

0.17

-point

0.17

/mobile

0.16

_xor

0.16

ternal

0.16

enge

0.16

Activations Density 0.047%

terms related to fixed characteristics or parameters in a system

No Comments

No Known Activations