INDEX

Explanations

food-related items and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

bak

-0.17

ury

-0.16

ekli

-0.16

tm

-0.16

 gens

-0.15

erer

-0.15

 bake

-0.15

mant

-0.14

yre

-0.14

ient

-0.14

POSITIVE LOGITS

 fork

0.18

 eating

0.17

fork

0.17

eating

0.17

 Eating

0.16

finish

0.16

portion

0.15

shima

0.15

asn

0.14

sat

0.14

Activations Density 0.128%

food-related items and actions

No Comments

No Known Activations