INDEX

Explanations

frequency and quantity descriptors, particularly the word "many"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

rett

-0.16

 Amir

-0.15

oly

-0.15

edly

-0.15

asi

-0.14

 PACKET

-0.14

acker

-0.14

rette

-0.14

arme

-0.14

 ÑĢÐ°Ð¼

-0.13

POSITIVE LOGITS

azole

0.16

 ways

0.15

anza

0.15

elu

0.15

otate

0.14

ToLocal

0.13

 IconData

0.13

 cazzo

0.13

ustil

0.13

conda

0.13

Activations Density 0.193%

frequency and quantity descriptors, particularly the word "many"

No Comments

No Known Activations