INDEX

Explanations

references to types and preparations of pasta dishes

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

ment

-0.15

ÏģÎ±Î½

-0.14

ane

-0.14

ãĤ·ãĥ¼

-0.14

pus

-0.14

 Sterling

-0.14

azon

-0.14

peats

-0.14

roperty

-0.13

 heights

-0.13

POSITIVE LOGITS

 pasta

0.27

 noodles

0.22

 spaghetti

0.19

 Pasta

0.19

uria

0.18

aghetti

0.18

 Giul

0.17

Italian

0.17

 Italian

0.17

oodles

0.17

Activations Density 0.036%

references to types and preparations of pasta dishes

No Comments

No Known Activations