INDEX

Explanations

the concept of hierarchical structures or classifications

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

heim

-0.15

_stdout

-0.15

za

-0.15

ily

-0.15

avo

-0.15

kus

-0.15

lesen

-0.14

Tob

-0.14

ktor

-0.14

oba

-0.14

POSITIVE LOGITS

rotch

0.16

 Stateless

0.14

.Designer

0.14

rel

0.14

afka

0.13

.jdesktop

0.13

 $č↵

0.13

anmar

0.13

ç¦

0.13

-LAST

0.13

Activations Density 0.106%

the concept of hierarchical structures or classifications

No Comments

No Known Activations