INDEX

Explanations

questions related to learning opportunities and programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Ð¾ÐºÐ¾Ð»

-0.15

rib

-0.14

ãĤªãĥª

-0.14

ForegroundColor

-0.14

bnb

-0.13

veloper

-0.13

 Crown

-0.13

ëĭ¹

-0.13

Presentation

-0.13

æĦıæĢĿ

-0.13

POSITIVE LOGITS

our

0.18

 ourselves

0.17

hurst

0.16

our

0.16

ourd

0.15

æĪĳä»¬çļĦ

0.15

 nuest

0.14

asal

0.14

artner

0.14

AUDIO

0.14

Activations Density 0.340%

questions related to learning opportunities and programs

No Comments

No Known Activations