INDEX

Explanations

instances of collaborative or participatory actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.16

al

-0.15

èĩ

-0.14

eu

-0.14

corp

-0.14

_ud

-0.14

allo

-0.14

POSITIVE LOGITS

infeld

0.16

ãĥªãĤ¢

0.16

ControlItem

0.15

/GPL

0.15

 cigaret

0.15

 Ãĩok

0.15

/slick

0.15

OMIC

0.14

.maps

0.14

scriptId

0.14

Activations Density 0.112%

instances of collaborative or participatory actions

No Comments

No Known Activations