INDEX

Explanations

the preposition "in" and its various contexts of use

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

æŁĦ

-0.18

ritch

-0.16

cem

-0.15

 Doch

-0.14

/arch

-0.14

 Unsupported

-0.14

folk

-0.13

olet

-0.13

arken

-0.13

COMPARE

-0.13

POSITIVE LOGITS

 late

0.22

 stages

0.20

 memory

0.17

 recognition

0.15

ismatic

0.14

{{{

0.14

 controversial

0.14

ive

0.14

aver

0.13

Activations Density 0.085%

the preposition "in" and its various contexts of use

No Comments

No Known Activations