INDEX

Explanations

references to therapy-related topics, particularly those concerning emotional well-being and mental health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 opak

-0.15

icles

-0.14

 Lamb

-0.14

HWND

-0.14

inea

-0.14

_BATCH

-0.14

 baptized

-0.13

UPS

-0.13

UPI

-0.13

POSITIVE LOGITS

 Mast

0.17

 AXIS

0.16

odor

0.16

-NLS

0.14

Sport

0.14

Ń

0.14

lyph

0.14

 Maher

0.14

ession

0.14

anger

0.14

Activations Density 0.135%

references to therapy-related topics, particularly those concerning emotional well-being and mental health

No Comments

No Known Activations