INDEX

Explanations

proper nouns related to individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

_frm

-0.15

enen

-0.15

appa

-0.15

NGX

-0.15

 probe

-0.14

 Tween

-0.14

æĪ

-0.14

tur

-0.14

Ð¾Ð¶

-0.14

ensch

-0.14

POSITIVE LOGITS

 societies

0.32

.union

0.26

 union

0.26

 society

0.25

SU

0.25

union

0.25

 Students

0.25

 student

0.25

 Union

0.25

 Student

0.24

Activations Density 0.054%

proper nouns related to individuals and organizations

No Comments

No Known Activations