INDEX

Explanations

references to functional compartments and features that enhance usability or organization

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

eo

-0.16

æ¼

-0.15

piel

-0.15

_SIMPLE

-0.14

jon

-0.14

apo

-0.13

chantment

-0.13

apg

-0.13

annes

-0.13

POSITIVE LOGITS

oot

0.15

lesc

0.15

 overwhelmed

0.15

¼åĲĪ

0.14

ettel

0.13

imei

0.13

rud

0.13

ç¾Ĭ

0.13

ä¸Ī

0.13

ANCES

0.13

Activations Density 0.099%

references to functional compartments and features that enhance usability or organization

No Comments

No Known Activations