INDEX

Explanations

references to specific dates and historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

artin

-0.15

åħĲ

-0.15

_startup

-0.15

ãģªãĤĵãģ¦

-0.15

dez

-0.15

ãģ¡ãģ¯

-0.14

ibur

-0.14

áº»

-0.14

onde

-0.14

åĺĽ

-0.14

POSITIVE LOGITS

 possibly

0.19

 late

0.19

probably

0.18

 probably

0.18

 maybe

0.17

 dates

0.17

 either

0.17

ca

0.17

possibly

0.16

Activations Density 0.049%

references to specific dates and historical contexts

No Comments

No Known Activations