INDEX

Explanations

prepositions indicating location or position

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ierarchical

-0.15

 ÙĬØ³

-0.14

.bpm

-0.14

 Pist

-0.13

avo

-0.13

 subscri

-0.13

idel

-0.13

.WindowManager

-0.13

vier

-0.13

 Tanz

-0.13

POSITIVE LOGITS

 fitte

0.18

baugh

0.16

ioxide

0.16

LLL

0.15

aus

0.15

.scalablytyped

0.14

ÏĨÎ¿

0.14

 sede

0.13

eron

0.13

sar

0.13

Activations Density 0.137%

prepositions indicating location or position

No Comments

No Known Activations