INDEX

Explanations

references to locations and landmarks in Cleveland

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Synopsis

-0.14

 sino

-0.13

 unless

-0.13

oeff

-0.13

.Android

-0.13

 regime

-0.13

aland

-0.12

min

-0.12

raphics

-0.12

ache

-0.12

POSITIVE LOGITS

 taken

0.27

 seen

0.26

 viewed

0.25

taken

0.23

detail

0.23

 showing

0.22

 detail

0.22

 Taken

0.21

 view

0.21

-detail

0.20

Activations Density 0.153%

references to locations and landmarks in Cleveland

No Comments

No Known Activations