INDEX

Explanations

references to time and organization structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

åľ¨

-0.21

å¤ªéĥİ

-0.17

GenerationStrategy

-0.16

ç«Ļåľ¨

-0.16

 shelf

-0.16

 Shelf

-0.15

_IRQn

-0.15

_into

-0.15

 doorstep

-0.15

 into

-0.15

POSITIVE LOGITS

 context

0.39

 guise

0.33

 manner

0.32

 sense

0.32

context

0.32

 midst

0.31

 contexts

0.31

 fashion

0.31

 ÙĪÙģÙĬ

0.30

 vicinity

0.27

Activations Density 1.680%

references to time and organization structures

No Comments

No Known Activations