INDEX

Explanations

occurrences of the word "this."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Barnett

-0.17

ACHER

-0.16

 this

-0.16

 recent

-0.15

 latest

-0.15

ubic

-0.15

mine

-0.15

on

-0.15

ward

-0.15

ted

-0.14

POSITIVE LOGITS

paged

0.20

 entry

0.20

ismu

0.18

 page

0.17

_Entry

0.17

 Week

0.16

 Month

0.16

 Item

0.16

isch

0.16

 Entry

0.15

Activations Density 0.163%

occurrences of the word "this."

No Comments

No Known Activations