INDEX

Explanations

specific names, brands, or entities associated with significant cultural impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

verture

-0.16

eum

-0.16

-esque

-0.16

puter

-0.15

kick

-0.15

ellas

-0.15

elerik

-0.15

nemonic

-0.14

agn

-0.14

li

-0.14

POSITIVE LOGITS

lessly

0.21

emiah

0.18

izabeth

0.18

headed

0.16

ilst

0.15

ched

0.14

laces

0.14

ĶåĽŀ

0.14

rice

0.14

Activations Density 2.479%

specific names, brands, or entities associated with significant cultural impact

No Comments

No Known Activations

specific names, brands, or entities associated with significant cultural impact

No Comments

No Known Activations