INDEX

Explanations

phrases indicating certainty or common observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.15

bod

-0.14

ÑĥÑĢÑģ

-0.14

GK

-0.13

sian

-0.13

á»©a

-0.13

aris

-0.13

serv

-0.13

POSITIVE LOGITS

dex

0.17

ìĬ¬

0.15

aign

0.14

ÑĤÐµÑģÑĮ

0.14

Pry

0.14

ccount

0.14

\Object

0.14

APT

0.14

ucket

0.14

icular

0.14

Activations Density 0.039%

phrases indicating certainty or common observations

No Comments

No Known Activations