INDEX

Explanations

terms related to official directives and legal mandates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Borders

-0.15

aver

-0.14

.outer

-0.14

wert

-0.14

æĽľ

-0.14

roads

-0.14

andra

-0.14

OOK

-0.13

ara

-0.13

POSITIVE LOGITS

_transient

0.16

essa

0.16

ahn

0.15

 intellig

0.15

Naw

0.15

zell

0.15

thin

0.14

anky

0.14

linger

0.14

Activations Density 0.018%

terms related to official directives and legal mandates

No Comments

No Known Activations