INDEX

Explanations

occurrences of the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ouri

-0.17

hurst

-0.15

povÄĽ

-0.15

cock

-0.14

heure

-0.14

oÅĻ

-0.14

agara

-0.14

rene

-0.14

glich

-0.14

akens

-0.13

POSITIVE LOGITS

aber

0.18

 Carpenter

0.16

lant

0.14

 Tanner

0.13

 Sponsored

0.13

dis

0.13

impse

0.13

ASHBOARD

0.13

 Marina

0.13

oda

0.13

Activations Density 0.083%

occurrences of the word "of."

No Comments

No Known Activations