INDEX

Explanations

occurrences of numerical data and specific tags related to events or topics

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

 punt

-0.15

ê²¬

-0.14

á»¥y

-0.14

znam

-0.14

caled

-0.14

FG

-0.13

abled

-0.13

ACA

-0.13

ksi

-0.13

ÏĥÎ¹

-0.13

POSITIVE LOGITS

Ã¥r

0.15

\\.

0.14

isson

0.14

 Colt

0.14

lero

0.14

.LookAndFeel

0.14

 anale

0.14

æģµ

0.13

Activations Density 0.008%

occurrences of numerical data and specific tags related to events or topics

No Comments

No Known Activations