INDEX

Explanations

references to mathematical theorems and lemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Prov

-0.14

oÅĻ

-0.14

.tom

-0.13

å¢¨

-0.13

íħĲ

-0.13

atti

-0.13

agine

-0.13

ibbon

-0.13

lÃ½

-0.13

hcp

-0.13

POSITIVE LOGITS

erras

0.15

.lin

0.14

 blogs

0.14

ToFront

0.14

 dual

0.14

 sled

0.13

 Tate

0.13

'),'

0.13

 Aviv

0.13

_inches

0.13

Activations Density 0.050%

references to mathematical theorems and lemmas

No Comments

No Known Activations