INDEX

Explanations

words associated with community events and group participation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

imd

-0.16

arian

-0.16

isel

-0.15

.bc

-0.15

quette

-0.15

ikan

-0.15

okino

-0.14

apore

-0.14

ERRU

-0.14

iyi

-0.14

POSITIVE LOGITS

 outside

0.21

 guest

0.19

 invite

0.19

 extern

0.19

 guests

0.19

 external

0.17

 staff

0.17

 civilian

0.17

 Outside

0.17

 Lair

0.16

Activations Density 0.104%

words associated with community events and group participation

No Comments

No Known Activations

words associated with community events and group participation

No Comments

No Known Activations