INDEX

Explanations

terms related to the effectiveness and value of services or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

uw

-0.16

owell

-0.16

izen

-0.16

ughs

-0.15

Ð¾Ð´Ð°

-0.15

Ð»Ð°ÑģÑĤÐ¸

-0.15

incr

-0.14

urge

-0.14

lush

-0.14

eson

-0.14

POSITIVE LOGITS

 enough

0.35

 Enough

0.23

ly

0.20

Enough

0.17

ness

0.16

/help

0.15

mente

0.15

ity

0.15

nier

0.15

ized

0.15

Activations Density 0.587%

terms related to the effectiveness and value of services or products

No Comments

No Known Activations