INDEX

Explanations

references to online events and their accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

EXTERN

-0.17

å£Ĭ

-0.16

gr

-0.15

ÙĪØ±Ø¯

-0.14

fri

-0.14

ossal

-0.14

dw

-0.14

lin

-0.14

PUT

-0.13

----------------------------------------------------------------------

-0.13

POSITIVE LOGITS

 investor

0.34

 investors

0.30

 Investor

0.30

 earnings

0.29

 conference

0.28

 Investors

0.26

 Conference

0.23

Conference

0.23

conference

0.23

 analyst

0.23

Activations Density 0.046%

references to online events and their accessibility

No Comments

No Known Activations