INDEX

Explanations

elements related to living conditions and community experiences

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

antu

-0.19

ghi

-0.17

 incorpor

-0.15

 prox

-0.15

inci

-0.14

 elsewhere

-0.14

 Plantae

-0.14

ãĥ³ãĤ¿

-0.14

UNG

-0.13

POSITIVE LOGITS

 inhabit

0.21

 inhab

0.20

oper

0.17

 oper

0.17

illo

0.17

occup

0.17

ãĤ¥

0.17

å¤Ħ

0.16

 ÙģÙĬÙĩ

0.16

 belong

0.16

Activations Density 0.104%

elements related to living conditions and community experiences

No Comments

No Known Activations