INDEX

Explanations

references to eating and food consumption

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

lei

-0.16

ement

-0.15

/current

-0.15

ouri

-0.14

iale

-0.14

adero

-0.14

esModule

-0.14

Äį

-0.14

ieux

-0.14

aml

-0.14

POSITIVE LOGITS

ijd

0.16

unma

0.15

kili

0.15

uary

0.15

ÃĹ↵↵

0.15

rieb

0.14

ourke

0.14

 GUIStyle

0.14

ropolis

0.14

ERGY

0.14

Activations Density 0.014%

references to eating and food consumption

No Comments

No Known Activations