INDEX

Explanations

questions and inquisitive phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

.openg

-0.15

oppins

-0.15

opp

-0.15

cz

-0.14

opp

-0.14

ichtig

-0.14

acro

-0.14

.gstatic

-0.14

POSITIVE LOGITS

 Deck

0.14

lify

0.14

 Mahm

0.14

ê»ĺ

0.14

Gow

0.14

loyd

0.14

toi

0.13

compan

0.13

inux

0.13

 pari

0.13

Activations Density 0.003%

questions and inquisitive phrases

No Comments

No Known Activations