INDEX

Explanations

names of prominent individuals in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

jom

-0.17

iyah

-0.16

raÃ§

-0.15

elia

-0.15

 itself

-0.15

_hpp

-0.15

venir

-0.14

deb

-0.14

etty

-0.14

å§ī

-0.14

POSITIVE LOGITS

Jr

0.19

MMdd

0.16

-ng

0.15

nesty

0.14

achinery

0.14

jr

0.14

Ð»Ð¾Ð¶

0.13

æĪ¶

0.13

 ÙĨÙģØ³Ùĩ

0.13

 Spart

0.13

Activations Density 0.566%

names of prominent individuals in various fields

No Comments

No Known Activations