INDEX

Explanations

terms related to motorcycles and motor vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

osate

-0.16

 Dark

-0.15

#.

-0.15

ath

-0.14

pty

-0.14

ï¼ĸ

-0.14

æĪ

-0.13

anke

-0.13

 sounding

-0.13

pite

-0.13

POSITIVE LOGITS

olah

0.14

loub

0.14

orpion

0.14

MOTE

0.14

fon

0.14

/schema

0.14

face

0.14

ASSERT

0.14

bour

0.14

Activations Density 0.100%

terms related to motorcycles and motor vehicles

No Comments

No Known Activations