INDEX

Explanations

questions and references to educational systems or policies

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

TRGL

-0.18

åħ

-0.16

ENÃį

-0.15

_php

-0.15

YYS

-0.15

 Braun

-0.15

Vad

-0.14

imar

-0.14

¥

-0.14

åŁŁ

-0.14

POSITIVE LOGITS

 GUID

0.19

UPC

0.17

PIL

0.16

åº§

0.16

èĪ¬

0.15

riterion

0.15

adir

0.14

Ð¾Ð¶Ðµ

0.14

æĮ

0.14

ittle

0.14

Activations Density 0.295%

questions and references to educational systems or policies

No Comments

No Known Activations