INDEX

Explanations

concepts related to human experiences and qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Mocks

-0.16

untu

-0.15

antha

-0.15

igs

-0.15

addy

-0.14

 preferredStyle

-0.14

leur

-0.14

emp

-0.14

ÑıÐ²

-0.14

POSITIVE LOGITS

ombat

0.17

 Rout

0.16

avax

0.15

odi

0.15

 compos

0.15

res

0.15

andi

0.14

positor

0.14

irts

0.14

irus

0.14

Activations Density 0.028%

concepts related to human experiences and qualities

No Comments

No Known Activations