INDEX

Explanations

terms and phrases related to mental health treatment and therapy techniques

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

Ink

-0.14

LETE

-0.14

SSI

-0.14

_compiler

-0.14

ÙĪÙĬØª

-0.14

Background

-0.14

Rem

-0.14

dbus

-0.14

kee

-0.14

POSITIVE LOGITS

 demonstrate

0.19

 Upon

0.18

 ability

0.18

Upon

0.18

Demon

0.18

 knowledge

0.17

 Demon

0.17

èĥ½å¤Ł

0.16

 awareness

0.16

 demonstrates

0.16

Activations Density 0.109%

terms and phrases related to mental health treatment and therapy techniques

No Comments

No Known Activations