INDEX

Explanations

numerical data, specifically referencing statistical values or metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÑĪÐºÐ°

-0.16

roe

-0.16

Ã¹

-0.15

hatt

-0.15

robe

-0.14

tridges

-0.14

luet

-0.13

Ã©ra

-0.13

ajo

-0.13

POSITIVE LOGITS

Qed

0.15

oundation

0.14

cad

0.14

keley

0.14

ehler

0.14

lik

0.14

Ð·Ð²

0.14

ĵĺ

0.13

usch

0.13

ENCES

0.13

Activations Density 0.051%

numerical data, specifically referencing statistical values or metrics

No Comments

No Known Activations