INDEX

Explanations

specific identifiers or proper nouns related to names or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

âĢ¦↵↵↵

-0.16

ebek

-0.15

iphers

-0.14

avax

-0.14

 podrob

-0.13

.InputStream

-0.13

Ã¨m

-0.13

arra

-0.13

CompatActivity

-0.13

POSITIVE LOGITS

arch

0.16

imu

0.15

vo

0.14

eng

0.14

wood

0.14

ock

0.14

 Crowley

0.14

 Schro

0.13

tar

0.13

 Arch

0.13

Activations Density 0.009%

specific identifiers or proper nouns related to names or titles

No Comments

No Known Activations