INDEX

Explanations

terms and concepts related to exploration, consumption, and definition in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ein

-0.20

ek

-0.17

ece

-0.16

arde

-0.15

ande

-0.14

.setPrototypeOf

-0.14

Cov

-0.14

ulent

-0.14

ServiceProvider

-0.14

POSITIVE LOGITS

ERS

0.24

ers

0.22

ings

0.21

ptions

0.21

ables

0.19

INGS

0.19

PTION

0.19

ersh

0.19

ethe

0.18

ableView

0.17

Activations Density 0.083%

terms and concepts related to exploration, consumption, and definition in various contexts

No Comments

No Known Activations