INDEX

Explanations

references to HTML tags and elements within the text

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

iele

-0.17

uitka

-0.17

alsy

-0.16

unh

-0.16

Naw

-0.14

Ð°Ð·Ð°

-0.14

azor

-0.14

ifu

-0.14

inding

-0.14

rena

-0.14

POSITIVE LOGITS

 kork

0.16

opsis

0.15

 Ekon

0.15

uÄį

0.14

æķ·

0.14

anceled

0.14

rol

0.14

avery

0.14

JsonValue

0.14

Î¼ÏīÎ½

0.13

Activations Density 0.160%

references to HTML tags and elements within the text

No Comments

No Known Activations