INDEX

Explanations

references to decision-making processes and the implications of those decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

peon

-0.16

ansson

-0.15

usercontent

-0.15

ierge

-0.15

LEGRO

-0.15

avr

-0.14

anda

-0.14

gaard

-0.14

GuidId

-0.14

ongoose

-0.14

POSITIVE LOGITS

itan

0.17

 Damen

0.16

 oneself

0.16

itt

0.15

 Holden

0.14

averse

0.14

æ¯Ķ

0.14

iner

0.14

oss

0.14

erm

0.14

Activations Density 1.173%

references to decision-making processes and the implications of those decisions

No Comments

No Known Activations