INDEX

Explanations

references to awards, accolades, and rankings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.20

-0.18

ollo

-0.15

HL

-0.15

olas

-0.15

olar

-0.15

ometer

-0.15

olor

-0.14

EP

-0.14

armor

-0.14

POSITIVE LOGITS

eed

0.19

igar

0.18

zego

0.17

backs

0.17

ieux

0.16

stead

0.15

LOUD

0.15

plx

0.15

azz

0.15

il

0.15

Activations Density 0.035%

references to awards, accolades, and rankings in various contexts

No Comments

No Known Activations