INDEX

Explanations

mentions of "America" and associated phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istica

-0.17

ilver

-0.16

rts

-0.16

ists

-0.16

ippo

-0.15

iform

-0.15

orthand

-0.15

ê·Ģ

-0.15

lak

-0.15

ToWorld

-0.15

POSITIVE LOGITS

 Ferr

0.21

JR

0.18

 BirleÅŁik

0.18

anness

0.17

 latina

0.16

 indiv

0.15

eturn

0.15

 Latina

0.15

KIT

0.15

Activations Density 0.026%

mentions of "America" and associated phrases

No Comments

No Known Activations