INDEX

Explanations

terms related to statistical and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

coe

-0.17

Leod

-0.17

ruk

-0.14

ihu

-0.14

-Co

-0.14

ole

-0.14

ãĥ¢

-0.13

ocÃª

-0.13

ContentSize

-0.13

rint

-0.13

POSITIVE LOGITS

ysl

0.16

ÑģÐ¾Ð»

0.15

ÑĤÐµÑĢ

0.15

ndon

0.15

lando

0.14

datatable

0.14

à¹Ģ

0.14

ederland

0.14

csr

0.14

erton

0.13

Activations Density 0.019%

terms related to statistical and numerical data

No Comments

No Known Activations