INDEX

Explanations

references to the word "latest" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

abella

-0.14

um

-0.14

ÙĪÙ¾

-0.14

lf

-0.14

ìĹŃ

-0.14

erken

-0.14

licated

-0.13

 next

-0.13

nemonic

-0.13

atto

-0.13

POSITIVE LOGITS

/current

0.23

0.22

sik

0.20

/latest

0.18

maal

0.17

icks

0.16

ëģ¼

0.16

ì§¸

0.15

Wyn

0.15

-ever

0.15

Activations Density 0.014%

references to the word "latest" in various contexts

No Comments

No Known Activations