INDEX

Explanations

time-related expressions and indications of communication

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

ustin

-0.14

isce

-0.14

azi

-0.14

 controversies

-0.14

owan

-0.14

etta

-0.14

Jak

-0.14

ÑĦÐ¸ÑĨÐ¸

-0.13

amburger

-0.13

anke

-0.13

POSITIVE LOGITS

 mant

0.17

 Mant

0.16

onse

0.15

itar

0.14

pis

0.14

rouw

0.14

tar

0.14

cce

0.14

.BackgroundColor

0.14

akis

0.14

Activations Density 0.002%

time-related expressions and indications of communication

No Comments

No Known Activations