INDEX

Explanations

references to academic involvement and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ystore

-0.18

trainer

-0.16

rade

-0.15

erse

-0.15

structors

-0.14

ense

-0.14

antlr

-0.14

ManagerInterface

-0.14

linewidth

-0.14

FTA

-0.14

POSITIVE LOGITS

0.16

ikk

0.16

0.15

strup

0.15

 Fake

0.14

 Editorial

0.14

pre

0.14

eli

0.14

 Languages

0.14

 pret

0.14

Activations Density 0.013%

references to academic involvement and achievements

No Comments

No Known Activations