INDEX

Explanations

references to time or specific moments

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

duct

-0.14

er

-0.14

orama

-0.14

depend

-0.14

iloc

-0.14

activ

-0.13

Ð²ÐµÑģÑĤÐ¸

-0.13

variants

-0.13

imals

-0.13

updates

-0.13

POSITIVE LOGITS

0.17

BufferData

0.16

ibox

0.16

à¹Īà¸Ńà¸¢

0.14

processable

0.13

usercontent

0.13

_firestore

0.13

reation

0.13

rollo

0.13

reno

0.13

Activations Density 0.062%

references to time or specific moments

No Comments

No Known Activations