INDEX

Explanations

references to sections and proofs in academic writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Kahn

-0.15

 Ø§ÙĦØ¹Ùħ

-0.14

.dds

-0.14

leh

-0.14

itude

-0.14

fir

-0.14

uir

-0.14

è¶

-0.13

Å¥

-0.13

marks

-0.13

POSITIVE LOGITS

0.15

etrofit

0.14

OLUMNS

0.14

Pow

0.13

ptal

0.13

 reciprocal

0.13

 crossed

0.13

Guy

0.13

&gt

0.13

acci

0.13

Activations Density 0.041%

references to sections and proofs in academic writing

No Comments

No Known Activations