INDEX

Explanations

instances of the word "From."

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

ukkit

-0.18

 Wake

-0.15

 Naked

-0.14

regor

-0.14

ÙĦ

-0.14

ersist

-0.14

Wake

-0.14

Rat

-0.14

iable

-0.14

POSITIVE LOGITS

odes

0.15

opot

0.15

ÑĤÐ°Ð±

0.15

idal

0.15

rÃ¡n

0.15

ardown

0.14

ØŃØ©

0.14

pections

0.14

onds

0.14

oldown

0.14

Activations Density 0.036%

instances of the word "From."

No Comments

No Known Activations