INDEX

Explanations

references to federal regulations and laws

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

áº¿u

-0.14

cus

-0.14

 Picasso

-0.14

ÐºÑĢÐµÑĤ

-0.13

bread

-0.13

Î¹Î²

-0.13

idas

-0.13

Indexes

-0.13

ce

-0.13

ats

-0.13

POSITIVE LOGITS

ized

0.20

/local

0.17

ised

0.17

ization

0.16

izado

0.15

'gc

0.15

izes

0.15

ity

0.14

izer

0.14

greens

0.14

Activations Density 0.018%

references to federal regulations and laws

No Comments

No Known Activations