INDEX

Explanations

references to known and unknown entities or concepts

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

isans

-0.17

 nett

-0.16

ero

-0.15

iggs

-0.15

erset

-0.15

rosso

-0.15

isode

-0.14

gross

-0.14

Ñİ

-0.14

artment

-0.14

POSITIVE LOGITS

ledge

0.17

0.16

liness

0.15

obil

0.14

Ã©mon

0.14

osh

0.14

nap

0.14

ingly

0.14

beros

0.14

ÑģÑĮ

0.14

Activations Density 0.048%

references to known and unknown entities or concepts

No Comments

No Known Activations