INDEX

Explanations

references to infinite series or mathematical constructs involving limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

oran

-0.16

Zus

-0.15

ÐµÐ¶

-0.15

 ngoáº¡i

-0.15

rtype

-0.14

sworth

-0.14

oram

-0.14

cloak

-0.14

Universal

-0.14

POSITIVE LOGITS

ä¹İ

0.16

suma

0.15

itor

0.15

 Hampton

0.15

uyo

0.14

utut

0.14

iginal

0.14

Mey

0.14

linha

0.14

perimental

0.14

Activations Density 0.006%

references to infinite series or mathematical constructs involving limits

No Comments

No Known Activations