INDEX

Explanations

references to legal or governmental entities and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ungan

-0.18

çĭĲ

-0.16

igned

-0.15

 Narr

-0.15

 Alto

-0.15

htable

-0.15

ÑĢÐµÑģ

-0.15

łĢ

-0.14

ãĢĤãĢĤ↵↵

-0.14

INO

-0.14

POSITIVE LOGITS

SEA

0.16

Brit

0.15

 Brit

0.15

 Seattle

0.14

ogui

0.14

ãĤ¹ãĤ¿ãĥ¼

0.14

 sometimes

0.14

agos

0.14

 presentations

0.14

cig

0.14

Activations Density 0.061%

references to legal or governmental entities and regulations

No Comments

No Known Activations