INDEX

Explanations

phrases that denote location or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 overd

-0.14

presso

-0.14

agar

-0.14

ecute

-0.14

ombo

-0.13

onga

-0.13

 bana

-0.13

azi

-0.13

 processData

-0.13

wards

-0.13

POSITIVE LOGITS

 which

0.20

 whom

0.16

 ìĿ´ëĬĶ

0.15

 ktÃ³re

0.15

cth

0.14

 kterÃ½ch

0.14

MAND

0.14

 ktÃ³

0.14

FAST

0.14

Î»Î»Î¹

0.14

Activations Density 0.144%

phrases that denote location or context

No Comments

No Known Activations