INDEX

Explanations

elements related to warnings and security measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Stories

-0.18

.datasets

-0.16

_models

-0.15

luet

-0.15

Instances

-0.15

brane

-0.15

_projects

-0.15

cation

-0.14

_APPS

-0.14

Repositories

-0.14

POSITIVE LOGITS

ones

0.21

 weights

0.19

 strings

0.18

 flags

0.18

 codes

0.18

itos

0.18

odes

0.18

 roots

0.17

 leads

0.16

Activations Density 0.346%

elements related to warnings and security measures

No Comments

No Known Activations