INDEX

Explanations

references to causes and effects, especially related to health and well-being

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

ti

-0.18

news

-0.17

ird

-0.15

ãģĵãģĿ

-0.15

 caus

-0.15

coming

-0.15

locking

-0.15

eters

-0.14

tid

-0.14

jam

-0.14

POSITIVE LOGITS

-effect

0.28

 cÃ©l

0.25

 cele

0.22

lesh

0.18

effect

0.18

iflower

0.17

yonel

0.16

lessly

0.16

ellation

0.16

 celebr

0.15

Activations Density 0.044%

references to causes and effects, especially related to health and well-being

No Comments

No Known Activations