INDEX

Explanations

references to political and healthcare-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

olut

-0.18

Ð¸ÑĤÐµÑĤ

-0.15

rix

-0.15

Ð¼ÐµÑĪ

-0.15

 Daughter

-0.14

umbo

-0.14

uden

-0.14

æĮ¯ãĤĬ

-0.14

rus

-0.14

ÃĴ

-0.14

POSITIVE LOGITS

 Randolph

0.16

acre

0.16

esse

0.15

æĪª

0.15

esch

0.14

 tongue

0.14

à¸ģà¸£

0.14

etal

0.14

ening

0.14

erton

0.13

Activations Density 0.027%

references to political and healthcare-related topics

No Comments

No Known Activations