INDEX

Explanations

organizations, individuals, or entities related to academic, governmental, or financial contexts

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

kara

-0.15

DSM

-0.14

reten

-0.14

 incons

-0.13

cano

-0.13

odem

-0.13

 Prod

-0.13

 Javier

-0.13

ottes

-0.13

nas

-0.13

POSITIVE LOGITS

*)((

0.16

opoly

0.15

ingo

0.15

isay

0.14

ï½¡

0.14

 IOCTL

0.14

Ã¡m

0.14

ertino

0.14

parity

0.14

Activations Density 0.039%

organizations, individuals, or entities related to academic, governmental, or financial contexts

No Comments

No Known Activations