INDEX

Explanations

references to speech or communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

tant

-0.16

å¤ĩ

-0.16

-0.15

 Chronicles

-0.15

leck

-0.15

icari

-0.15

ged

-0.14

ÑĢÐ¾Ñĩ

-0.14

ubat

-0.14

 Ã©lect

-0.14

POSITIVE LOGITS

à¹Ģà¸ģà¸Ńà¸£

0.17

/write

0.16

able

0.15

outed

0.15

-minded

0.15

-speaking

0.14

ernes

0.14

 Bureau

0.14

OVE

0.14

_COMPARE

0.13

Activations Density 0.048%

references to speech or communication

No Comments

No Known Activations