INDEX

Explanations

complex ideas around personal beliefs and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

agne

-0.18

.club

-0.15

rire

-0.14

ÑĢÐ°Ðº

-0.14

eter

-0.14

.ObjectModel

-0.14

phant

-0.13

olla

-0.13

ieber

-0.13

POSITIVE LOGITS

ervas

0.16

altet

0.14

Smarty

0.14

Fcn

0.14

entic

0.14

çĽ¤

0.14

fighters

0.14

_:*

0.14

enci

0.14

rem

0.13

Activations Density 0.152%

complex ideas around personal beliefs and experiences

No Comments

No Known Activations