INDEX

Explanations

fragments indicating a sense of being new or inexperienced

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Sea

-0.14

 Cher

-0.14

Ret

-0.14

imson

-0.14

isia

-0.14

odem

-0.14

utf

-0.14

urge

-0.14

 Chase

-0.14

mented

-0.14

POSITIVE LOGITS

 Walters

0.16

Ã¼rger

0.16

illusion

0.15

ë¡±

0.15

ling

0.15

illus

0.15

adaptive

0.14

Ø§ÙĨÙĩ

0.14

ienen

0.14

usband

0.14

Activations Density 0.018%

fragments indicating a sense of being new or inexperienced

No Comments

No Known Activations