INDEX

Explanations

references to geographical locations and administrative divisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

lagen

-0.17

><![

-0.17

calar

-0.16

Ð¾Ð»Ñı

-0.14

apollo

-0.14

orsch

-0.14

ijken

-0.14

roker

-0.14

ffen

-0.14

instr

-0.14

POSITIVE LOGITS

 located

0.20

 situ

0.18

 situated

0.18

 Located

0.17

 náº±m

0.16

 ubic

0.16

located

0.16

ä½įäºİ

0.15

sit

0.15

Sit

0.14

Activations Density 0.100%

references to geographical locations and administrative divisions

No Comments

No Known Activations