INDEX

Explanations

inquiries and considerations regarding motivations and reasons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

kv

-0.15

ãĥĳãĥ³

-0.14

kel

-0.14

åĹ

-0.14

 INDIRECT

-0.13

CreateInfo

-0.13

ubre

-0.13

åįĶ

-0.13

ytut

-0.13

etik

-0.13

POSITIVE LOGITS

achat

0.16

ales

0.15

ofs

0.15

erto

0.15

ienen

0.14

atat

0.14

jian

0.14

ãģ¹ãģį

0.14

amarin

0.14

 Chair

0.14

Activations Density 0.131%

inquiries and considerations regarding motivations and reasons

No Comments

No Known Activations