INDEX

Explanations

references to living individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÑĢÐ°ÑģÑĤ

-0.14

.createServer

-0.14

ataset

-0.14

oningen

-0.14

zes

-0.14

unb

-0.14

á»¯ng

-0.14

_SLAVE

-0.14

anche

-0.14

.Guna

-0.14

POSITIVE LOGITS

RY

0.17

icode

0.15

lauf

0.15

quire

0.15

eworthy

0.14

rosso

0.14

swire

0.14

 Resorts

0.14

chs

0.14

:animated

0.14

Activations Density 0.005%

references to living individuals or groups

No Comments

No Known Activations