INDEX

Explanations

specific mathematical notations or symbols related to proofs and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

-0.17

Î®

-0.16

éłĵ

-0.15

endale

-0.15

ãĥ¼ãĥŀ

-0.15

 âĸĪ

-0.14

eldon

-0.14

uir

-0.14

(___

-0.14

éļª

-0.14

POSITIVE LOGITS

anio

0.15

 Browse

0.15

aise

0.15

ÑĤÐ¸Ð½

0.15

gary

0.14

inho

0.14

 Patri

0.14

Browse

0.14

 Greg

0.14

ippers

0.13

Activations Density 0.005%

specific mathematical notations or symbols related to proofs and functions

No Comments

No Known Activations