INDEX

Explanations

references to community involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

urve

-0.15

hazi

-0.15

linger

-0.14

deaux

-0.14

edom

-0.14

NESS

-0.14

iness

-0.14

ardu

-0.13

htags

-0.13

ig

-0.13

POSITIVE LOGITS

wide

0.19

-wide

0.19

ourn

0.18

èħ

0.15

/community

0.15

CPP

0.15

 Wich

0.14

ëŀ

0.14

 Schultz

0.14

 Moran

0.14

Activations Density 0.032%

references to community involvement

No Comments

No Known Activations