INDEX

Explanations

references to educational resources and tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

avir

-0.17

_PROF

-0.15

ãĥ¼ãĥª

-0.15

idis

-0.15

 Suppress

-0.14

Lag

-0.14

Suppress

-0.14

UME

-0.13

ETERS

-0.13

 Ð¿Ð¾Ð´Ð°Ð²

-0.13

POSITIVE LOGITS

GC

0.31

OCR

0.31

 revision

0.30

 Revision

0.30

revision

0.28

OCR

0.28

gc

0.28

Revision

0.27

GC

0.27

 exam

0.26

Activations Density 0.055%

references to educational resources and tools

No Comments

No Known Activations