INDEX

Explanations

claims or assertions made about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

asty

-0.17

ibase

-0.15

ebo

-0.15

ARRANT

-0.14

ijkstra

-0.14

reon

-0.14

intColor

-0.14

ÏĥÎ¿Ïħ

-0.14

 verdiÄŁi

-0.14

Ð°ÑĪÐ°

-0.14

POSITIVE LOGITS

cce

0.16

ocode

0.16

ÑĢÑĥÐ¿

0.15

 loss

0.15

ching

0.14

chod

0.14

Ĳ

0.14

 code

0.14

loss

0.14

Activations Density 0.169%

claims or assertions made about various subjects

No Comments

No Known Activations