INDEX

Explanations

terms related to legal and regulatory contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

-0.16

-0.15

_SAMPL

-0.15

iaux

-0.14

lice

-0.14

utex

-0.14

terior

-0.14

ĥn

-0.14

 Bless

-0.14

-0.13

POSITIVE LOGITS

adro

0.15

rum

0.15

rops

0.15

ãĥ£

0.14

BarItem

0.14

.communication

0.14

eeper

0.14

 path

0.14

unos

0.14

zbo

0.14

Activations Density 0.002%

terms related to legal and regulatory contexts

No Comments

No Known Activations