INDEX

Explanations

references to the USA or related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 usual

-0.16

æ¥Ń

-0.15

aurus

-0.15

adem

-0.15

ãĥŃãĥ³

-0.14

 ucwords

-0.14

ÑģÑĤÐ°

-0.14

ÑĢÐ°ÑħÐ¾Ð²

-0.14

 Fitz

-0.14

uber

-0.14

POSITIVE LOGITS

merican

0.20

à¸²à¸ĩ

0.16

 Latina

0.15

eno

0.15

ä½

0.14

meric

0.14

 latter

0.14

ndef

0.14

-Agent

0.13

Ø±ÙĬÙĥÙĬ

0.13

Activations Density 0.023%

references to the USA or related contexts

No Comments

No Known Activations