INDEX

Explanations

references to annual reports and related documentation

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

 Holding

-0.15

ichert

-0.15

ammer

-0.15

rese

-0.14

 Bank

-0.14

ord

-0.13

æĥħ

-0.13

acic

-0.13

-ul

-0.13

ÐĿÐ¯

-0.13

POSITIVE LOGITS

ahren

0.19

znik

0.18

 reporting

0.17

vana

0.16

raquo

0.16

 report

0.15

.AddListener

0.15

cion

0.15

viewer

0.15

 Report

0.14

Activations Density 0.062%

references to annual reports and related documentation

No Comments

No Known Activations