INDEX

Explanations

references to health-related topics and emotional impacts stemming from various medical conditions

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

 Eventually

-0.15

ÏĥÎ¿Î½

-0.14

 eventually

-0.14

anio

-0.14

_ER

-0.14

Eventually

-0.14

kazy

-0.13

 ÙħØ«Ø¨Øª

-0.13

 elsewhere

-0.13

indle

-0.13

POSITIVE LOGITS

 after

0.84

 post

0.73

after

0.68

 Ð¿Ð¾ÑģÐ»Ðµ

0.62

 AFTER

0.62

 dopo

0.61

_after

0.60

 After

0.59

After

0.59

 efter

0.56

Activations Density 0.455%

references to health-related topics and emotional impacts stemming from various medical conditions

No Comments

No Known Activations

references to health-related topics and emotional impacts stemming from various medical conditions

No Comments

No Known Activations