INDEX

Explanations

instances of year numbers or dates

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

uel

-0.16

ieg

-0.15

ipro

-0.15

Laz

-0.15

ener

-0.15

iko

-0.15

kol

-0.15

 LENG

-0.15

tron

-0.14

aldi

-0.14

POSITIVE LOGITS

ewood

0.15

 torino

0.15

_qs

0.14

jedn

0.14

oden

0.14

-aos

0.14

é¼

0.14

íĳľ

0.13

 ëĵ¯

0.13

OME

0.13

Activations Density 0.002%

instances of year numbers or dates

No Comments

No Known Activations