INDEX

Explanations

specific technical terms and indicators of formal processes or classifications

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

bine

-0.16

spender

-0.16

eturn

-0.14

skyt

-0.14

elyn

-0.14

PFN

-0.14

rrha

-0.13

intel

-0.13

 dÃ©p

-0.13

dna

-0.13

POSITIVE LOGITS

isco

0.16

adal

0.14

oston

0.14

Ø©

0.14

 maintain

0.14

 maint

0.14

 Mundo

0.13

ont

0.13

ìĦľ

0.13

Activations Density 0.042%

specific technical terms and indicators of formal processes or classifications

No Comments

No Known Activations

specific technical terms and indicators of formal processes or classifications

No Comments

No Known Activations