INDEX

Explanations

references to different editions of publications or products

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

eon

-0.18

ãģªãĤĭ

-0.17

ÙĥØªÙĪØ±

-0.15

andal

-0.15

izza

-0.15

*)_

-0.14

 konkrÃ©t

-0.14

éŀĭ

-0.14

overn

-0.14

>NN

-0.14

POSITIVE LOGITS

 Pace

0.14

wu

0.14

Ø§Ø´Øª

0.14

leness

0.14

ç«ł

0.14

eny

0.14

 Vest

0.14

alue

0.14

isti

0.14

ify

0.13

Activations Density 0.008%

references to different editions of publications or products

No Comments

No Known Activations