INDEX

Explanations

occurrences of the word "ile" and its variations, alongside significant character names or titles

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

 Robbins

-0.18

akk

-0.17

stvo

-0.16

-tm

-0.15

resi

-0.15

 è¢

-0.14

sett

-0.14

 Ballard

-0.14

sembly

-0.14

 Blonde

-0.13

POSITIVE LOGITS

0.17

.Abstractions

0.16

abil

0.14

lag

0.14

 abstract

0.14

auge

0.14

ToFront

0.14

Bac

0.14

 KeyValuePair

0.14

 Bair

0.14

Activations Density 0.015%

occurrences of the word "ile" and its variations, alongside significant character names or titles

No Comments

No Known Activations