INDEX

Explanations

technical terms and codes related to medical or operational settings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

oplevel

-0.17

obot

-0.17

 russ

-0.16

 Russ

-0.15

rette

-0.15

 Russell

-0.15

irma

-0.14

udad

-0.14

patch

-0.14

Russ

-0.14

POSITIVE LOGITS

istant

0.15

aly

0.15

 Carrie

0.14

hit

0.14

igg

0.14

ith

0.14

éĢŁ

0.14

 torino

0.14

 Prospect

0.14

&view

0.13

Activations Density 0.022%

technical terms and codes related to medical or operational settings

No Comments

No Known Activations