INDEX

Explanations

references to discussions or topics in online forums

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 trap

-0.16

ulant

-0.15

ifo

-0.14

.codes

-0.14

 Trap

-0.14

xAB

-0.14

ëĭĪìĬ¤

-0.14

lette

-0.14

pron

-0.14

led

-0.13

POSITIVE LOGITS

izzer

0.16

 Warn

0.15

.docs

0.14

ibox

0.14

ÏĥÎ¿Ïħ

0.14

.GroupLayout

0.14

Î·Î³

0.14

aklÄ±

0.14

Meg

0.13

deÅŁ

0.13

Activations Density 0.012%

references to discussions or topics in online forums

No Comments

No Known Activations