INDEX

Explanations

references to occurrences and relationships in the context of a narrative or event

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

UME

-0.17

lero

-0.15

Éµ

-0.15

nict

-0.14

tolua

-0.14

 prin

-0.14

elsey

-0.14

uet

-0.13

bia

-0.13

eyin

-0.13

POSITIVE LOGITS

umn

0.16

emme

0.15

rell

0.15

ilder

0.14

.onStart

0.14

uda

0.14

Ð°Ñİ

0.14

ÏĦÎ¿Î»

0.14

leÅŁme

0.14

asts

0.13

Activations Density 0.432%

references to occurrences and relationships in the context of a narrative or event

No Comments

No Known Activations