INDEX

Explanations

references to sections and theorems in academic papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

velt

-0.15

enza

-0.15

.InnerException

-0.14

Ð²ÑĸÐ»ÑĮ

-0.14

Lon

-0.14

akit

-0.14

ÐĤ

-0.13

indi

-0.13

colo

-0.13

feb

-0.13

POSITIVE LOGITS

infeld

0.15

hdr

0.15

Youtube

0.14

ãĥĥãĤ·ãĥ¥

0.14

respons

0.14

 è£

0.14

ref

0.14

arella

0.14

Ð¾Ð´Ñĥ

0.14

ref

0.14

Activations Density 0.053%

references to sections and theorems in academic papers

No Comments

No Known Activations