INDEX

Explanations

sequences of numeric values or numerical codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-0.25

ÏĤ

-0.19

ska

-0.15

iffe

-0.14

sak

-0.14

Woj

-0.14

ãģıãĤī

-0.14

.sax

-0.14

erti

-0.14

sian

-0.14

POSITIVE LOGITS

dyby

0.17

erken

0.16

aters

0.16

eks

0.16

ãĥ¼ãĥĸ

0.16

aucoup

0.15

place

0.14

ordial

0.14

ected

0.13

 unpack

0.13

Activations Density 0.017%

sequences of numeric values or numerical codes

No Comments

No Known Activations