INDEX

Explanations

occurrences of numbers and dates in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

eniable

-0.16

etten

-0.16

utzer

-0.16

&e

-0.15

qua

-0.14

 Cros

-0.14

ilim

-0.14

[email

-0.14

ÐµÑĤÑĥ

-0.14

vala

-0.14

POSITIVE LOGITS

acket

0.16

ackets

0.16

.fastjson

0.14

 AltÄ±n

0.14

.wik

0.13

desktop

0.13

 liquids

0.13

 everywhere

0.13

kara

0.13

Activations Density 0.407%

occurrences of numbers and dates in the text

No Comments

No Known Activations