INDEX

Explanations

references to historical figures and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

STA

-0.20

eca

-0.19

_sta

-0.15

.wx

-0.15

.dsl

-0.14

ehler

-0.14

 Feinstein

-0.14

ony

-0.14

ê

-0.13

zz

-0.13

POSITIVE LOGITS

iping

0.14

axe

0.14

plat

0.14

iami

0.14

amps

0.14

[:]

0.13

oshi

0.13

ãĤıãģĳ

0.13

aler

0.13

Ð¾ÐºÐ¸

0.13

Activations Density 0.020%

references to historical figures and their activities

No Comments

No Known Activations