INDEX

Explanations

specific character attributes and actions in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-0.17

CppType

-0.17

 iken

-0.16

regor

-0.15

 previously

-0.15

hte

-0.14

GuidId

-0.14

 Previously

-0.14

Ã±ana

-0.13

UsageId

-0.13

POSITIVE LOGITS

 everybody

0.17

asy

0.15

 inherited

0.14

ElementsBy

0.14

ugin

0.14

éĺ´

0.14

igr

0.14

0.13

bil

0.13

 nobody

0.13

Activations Density 0.036%

specific character attributes and actions in a narrative context

No Comments

No Known Activations

specific character attributes and actions in a narrative context

No Comments

No Known Activations