INDEX

Explanations

phrases related to general information and resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ľ°

-0.16

hus

-0.16

riger

-0.15

stell

-0.14

 Husband

-0.14

 Consent

-0.14

 cons

-0.14

Wilson

-0.14

²

-0.13

 Wilson

-0.13

POSITIVE LOGITS

heim

0.16

ouch

0.15

 Quadr

0.15

apolis

0.14

 å¤ı

0.14

ingt

0.14

 quadr

0.14

ulpt

0.14

BLE

0.14

ampo

0.13

Activations Density 0.034%

phrases related to general information and resources

No Comments

No Known Activations