INDEX

Explanations

references to a specific chef or individual named Mich

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

jde

-0.18

cone

-0.17

 Hath

-0.16

eza

-0.15

PIP

-0.15

geois

-0.15

ftware

-0.15

iture

-0.15

ahren

-0.14

 Aires

-0.14

POSITIVE LOGITS

elin

0.24

angelo

0.24

elson

0.23

ail

0.21

igan

0.21

igans

0.19

els

0.18

gan

0.18

eline

0.18

Ã¨le

0.17

Activations Density 0.007%

references to a specific chef or individual named Mich

No Comments

No Known Activations