INDEX

Explanations

numerical values related to historical or statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ã¤m

-0.15

aspers

-0.15

erno

-0.15

-0.14

ainless

-0.14

ibbon

-0.14

ewire

-0.13

ettle

-0.13

uesta

-0.13

ramework

-0.13

POSITIVE LOGITS

oxel

0.16

Uploaded

0.14

 destinationViewController

0.14

Ø·Ø¨

0.14

oner

0.14

DDL

0.14

ries

0.13

otto

0.13

cron

0.13

ellipsis

0.13

Activations Density 0.087%

numerical values related to historical or statistical data

No Comments

No Known Activations