INDEX

Explanations

proper nouns and specific named entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

angkan

-0.15

ASURE

-0.15

awy

-0.14

osaur

-0.14

à¸Ĭà¸£

-0.14

 tato

-0.14

à¸£à¸¡

-0.14

å°ĳå¹´

-0.14

ogh

-0.13

ulator

-0.13

POSITIVE LOGITS

others

0.15

 IOCTL

0.14

ialis

0.14

oggler

0.14

ews

0.14

Ð¾Ð

0.14

asso

0.14

áº¹

0.14

FIX

0.13

 others

0.13

Activations Density 0.238%

proper nouns and specific named entities

No Comments

No Known Activations