INDEX

Explanations

descriptions of emotional depth and human-like qualities in characters and situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

erva

-0.16

 Brunswick

-0.15

isia

-0.14

ually

-0.14

loat

-0.14

ationally

-0.14

Bea

-0.13

 Kens

-0.13

 Resident

-0.13

fait

-0.13

POSITIVE LOGITS

ÐµÐºÐ°ÑĢ

0.17

 aspect

0.17

 element

0.16

igkeit

0.15

egree

0.15

hone

0.15

 feel

0.15

egen

0.15

atown

0.15

interop

0.14

Activations Density 0.182%

descriptions of emotional depth and human-like qualities in characters and situations

No Comments

No Known Activations