INDEX

Explanations

references to editions or versions of publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

jni

-0.15

à¤¬à¤°

-0.14

ere

-0.14

-headed

-0.14

embr

-0.14

epy

-0.14

SCAN

-0.13

achten

-0.13

htar

-0.13

/goto

-0.13

POSITIVE LOGITS

olik

0.16

orde

0.15

 Chase

0.14

ieux

0.14

cloud

0.14

 khoa

0.14

ainter

0.14

 treff

0.14

ERGY

0.14

 Chips

0.13

Activations Density 0.007%

references to editions or versions of publications

No Comments

No Known Activations