INDEX

Explanations

terms related to potential risks and consequences in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.16

 hang

-0.15

irth

-0.15

 Angola

-0.14

 techn

-0.14

 Herc

-0.13

 Hang

-0.13

vig

-0.13

Fet

-0.13

á»ĩu

-0.13

POSITIVE LOGITS

achable

0.17

iare

0.16

 Reyn

0.16

lian

0.15

chÃ©

0.15

asco

0.15

ãĥĨãĥ«

0.15

jsc

0.14

isÃŃ

0.14

onis

0.14

Activations Density 0.374%

terms related to potential risks and consequences in various contexts

No Comments

No Known Activations