INDEX

Explanations

references to purity or pure concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

shelf

-0.19

perature

-0.16

uality

-0.15

itr

-0.15

reuse

-0.15

atical

-0.15

sel

-0.15

chy

-0.15

mun

-0.14

ÏĥÏĩ

-0.14

POSITIVE LOGITS

bred

0.34

pure

0.30

 Pure

0.28

 pure

0.26

Pure

0.26

foy

0.25

st

0.24

PURE

0.23

ç²

0.23

eing

0.23

Activations Density 0.015%

references to purity or pure concepts

No Comments

No Known Activations