INDEX

Explanations

references to valuable items or concepts, particularly those that suggest rarity or high worth

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

agn

-0.17

_requires

-0.15

go

-0.15

zial

-0.14

eo

-0.14

ForResult

-0.14

sembly

-0.14

cono

-0.14

\<^

-0.14

eco

-0.13

POSITIVE LOGITS

èĪ¬

0.15

baum

0.14

&s

0.14

ieber

0.14

coil

0.14

ilde

0.14

SPA

0.14

hest

0.14

mond

0.14

utzer

0.13

Activations Density 0.037%

references to valuable items or concepts, particularly those that suggest rarity or high worth

No Comments

No Known Activations