INDEX

Explanations

references to places and geographic locations

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

eneric

-0.15

ey

-0.15

eya

-0.15

eyn

-0.14

.tencent

-0.14

ieval

-0.14

 Bless

-0.14

enor

-0.14

enis

-0.13

POSITIVE LOGITS

 County

0.23

çľĮ

0.18

 county

0.18

 COUNTY

0.18

County

0.17

ombre

0.17

ongan

0.16

'=>['

0.16

-widgets

0.15

vincia

0.15

Activations Density 0.125%

references to places and geographic locations

No Comments

No Known Activations