INDEX

Explanations

references to locations and the concept of home

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ikki

-0.15

alion

-0.15

SX

-0.15

oord

-0.15

mbH

-0.15

anio

-0.15

raith

-0.15

blr

-0.14

lez

-0.14

POSITIVE LOGITS

0.18

 definition

0.15

Ill

0.15

 Mish

0.14

ad

0.14

em

0.14

 Begin

0.14

à¤¿à¤·

0.14

 incon

0.14

Bun

0.14

Activations Density 0.321%

references to locations and the concept of home

No Comments

No Known Activations