INDEX

Explanations

entities and terms related to mental health and interventions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

AINED

-0.14

Did

-0.14

BO

-0.14

æ¸

-0.14

plied

-0.14

ulen

-0.13

idth

-0.13

ict

-0.13

ilon

-0.13

 VerfÃ¼gung

-0.13

POSITIVE LOGITS

 zosta

0.21

was

0.19

 wordt

0.19

 zost

0.19

 werd

0.19

 will

0.17

osta

0.17

 became

0.17

 becomes

0.16

 Ð¼Ð¾Ð¶Ð½Ð¾

0.16

Activations Density 0.387%

entities and terms related to mental health and interventions

No Comments

No Known Activations