INDEX

Explanations

phrases indicating uniqueness or singularity in events or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

boom

-0.14

Ð½ÐµÐ½

-0.14

RIX

-0.14

idding

-0.13

iÅ¾

-0.13

áºŃm

-0.13

 Latest

-0.13

ict

-0.13

Ã©ro

-0.13

latest

-0.13

POSITIVE LOGITS

-ever

0.53

 ever

0.47

ever

0.41

Ever

0.26

 EVER

0.26

 Ever

0.23

 jamais

0.22

-of

0.22

of

0.21

 major

0.20

Activations Density 0.065%

phrases indicating uniqueness or singularity in events or objects

No Comments

No Known Activations