INDEX

Explanations

negative attributes and limitations associated with software or technology

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

anan

-0.16

pter

-0.15

 Pest

-0.14

indre

-0.14

.invoice

-0.14

 plÃ¡

-0.14

rote

-0.14

antly

-0.14

ournal

-0.14

Æ°á»£

-0.14

POSITIVE LOGITS

 thereby

0.17

ikh

0.16

making

0.15

 thus

0.15

ìį¨

0.15

kh

0.15

 leaving

0.14

result

0.14

 hence

0.14

fft

0.14

Activations Density 0.285%

negative attributes and limitations associated with software or technology

No Comments

No Known Activations