INDEX

Explanations

references to specific individuals, particularly in the context of political events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.ua

-0.15

ÙħØ¬

-0.14

fty

-0.14

Ø¨Ø§ØŃ

-0.14

 upset

-0.14

_modal

-0.14

adi

-0.14

sehen

-0.14

stvÃŃ

-0.13

æŁ³

-0.13

POSITIVE LOGITS

stp

0.18

 Illinois

0.17

 Chicago

0.17

afil

0.16

azor

0.16

igy

0.15

/ic

0.14

SizeMode

0.14

iales

0.14

à¸Ļà¸§

0.14

Activations Density 0.001%

references to specific individuals, particularly in the context of political events

No Comments

No Known Activations