INDEX

Explanations

architectural and historical landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

íĥĪ

-0.15

CCI

-0.14

ayah

-0.14

iese

-0.14

wn

-0.13

ugu

-0.13

 ä¸ĵ

-0.13

ãģ°ãģĭãĤĬ

-0.13

_AUX

-0.13

_native

-0.13

POSITIVE LOGITS

 dating

0.17

dating

0.16

arrant

0.16

 where

0.16

 Dating

0.16

 housing

0.15

 hosts

0.15

Dating

0.15

 founded

0.14

 date

0.14

Activations Density 0.123%

architectural and historical landmarks

No Comments

No Known Activations