INDEX

Explanations

references to online platforms and digital communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Bieber

-0.15

aat

-0.15

 promot

-0.15

rell

-0.15

ssue

-0.14

aret

-0.14

 Jesse

-0.14

asio

-0.14

ceed

-0.14

iegel

-0.14

POSITIVE LOGITS

anja

0.16

kud

0.15

ENCHMARK

0.14

overn

0.14

cki

0.14

_equiv

0.14

 Ferd

0.14

adel

0.13

 lawy

0.13

hone

0.13

Activations Density 0.159%

references to online platforms and digital communication

No Comments

No Known Activations