INDEX

Explanations

references to fiscal years and financial figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

uela

-0.17

sez

-0.17

yna

-0.15

otti

-0.15

za

-0.15

çĢ¬

-0.14

 liter

-0.14

utsch

-0.14

 Rica

-0.14

UDGE

-0.14

POSITIVE LOGITS

tery

0.16

robe

0.15

Handled

0.14

embre

0.14

ACHE

0.13

oucher

0.13

apter

0.13

tram

0.13

elan

0.13

tl

0.13

Activations Density 0.030%

references to fiscal years and financial figures

No Comments

No Known Activations