INDEX

Explanations

references to placeholder pages or individuals not currently associated with a site

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

tat

-0.15

 Gardner

-0.14

-urlencoded

-0.14

airs

-0.14

Ð¾Ð±Ð¾Ð²

-0.14

stdafx

-0.14

pers

-0.14

POSITIVE LOGITS

pher

0.16

éĻµ

0.16

cko

0.15

lify

0.15

 page

0.14

/ay

0.14

ifu

0.14

cury

0.14

 legacy

0.14

iet

0.14

Activations Density 0.010%

references to placeholder pages or individuals not currently associated with a site

No Comments

No Known Activations