INDEX

Explanations

phrases indicating actions or events involving participation or involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ehler

-0.15

 Eaton

-0.15

ssel

-0.14

oÅ¡

-0.14

sim

-0.14

rapy

-0.14

Ut

-0.14

 Princip

-0.14

.Exceptions

-0.14

 Vibr

-0.14

POSITIVE LOGITS

ately

0.17

iod

0.17

pon

0.15

nex

0.15

pts

0.14

bsd

0.14

 Rescue

0.14

ãĥ¬ãĥĥãĥĪ

0.14

æķĳ

0.13

 rescue

0.13

Activations Density 0.177%

phrases indicating actions or events involving participation or involvement

No Comments

No Known Activations