INDEX

Explanations

multiple mentions of the word "fact"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

anta

-0.16

{{{

-0.14

ëŁ¬

-0.14

å¿Ļ

-0.14

Monad

-0.14

 Ð·Ð°ÐºÐ»Ð°Ð´

-0.14

 Monad

-0.14

imo

-0.14

.Designer

-0.14

ìĻ¸

-0.14

POSITIVE LOGITS

eid

0.15

ease

0.14

eo

0.14

 verte

0.14

unds

0.14

Ral

0.14

annel

0.14

0.13

à¸ĩà¸Ĺ

0.13

rames

0.13

Activations Density 0.014%

multiple mentions of the word "fact"

No Comments

No Known Activations