INDEX

Explanations

specific nouns related to entities and configurations

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

sson

-0.16

ums

-0.16

 Licht

-0.14

idor

-0.14

egl

-0.14

cura

-0.14

DUCT

-0.13

 Amar

-0.13

adow

-0.13

oids

-0.13

POSITIVE LOGITS

 Awake

0.16

rous

0.16

oton

0.15

ÏĥÏĦÎµ

0.15

leans

0.14

æį·

0.14

çľł

0.14

pons

0.14

0.13

Activations Density 0.021%

specific nouns related to entities and configurations

No Comments

No Known Activations