INDEX

Explanations

references to computational outcomes or results obtained from calculations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 king

-0.16

 emperor

-0.14

uale

-0.14

cio

-0.14

éľŀ

-0.14

lfw

-0.13

decorators

-0.13

allo

-0.13

 King

-0.13

ails

-0.13

POSITIVE LOGITS

urdy

0.18

0.16

cast

0.16

yonel

0.15

 MetroFramework

0.14

bote

0.14

 results

0.14

cribe

0.14

ilst

0.14

orden

0.14

Activations Density 0.113%

references to computational outcomes or results obtained from calculations

No Comments

No Known Activations