INDEX

Explanations

URLs and links to academic papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

å¿Ĺ

-0.14

alla

-0.14

 pockets

-0.14

bert

-0.14

AndView

-0.13

ENTE

-0.13

dej

-0.13

ewan

-0.13

enty

-0.13

POSITIVE LOGITS

mrt

0.17

abra

0.16

MEDIA

0.15

Ø¯Ø§Ùħ

0.14

_SOFT

0.14

ahlen

0.14

ikel

0.14

esto

0.14

://

0.14

ONGL

0.14

Activations Density 0.004%

URLs and links to academic papers

No Comments

No Known Activations