INDEX

Explanations

references to storage facilities and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

storage

-0.25

_storage

-0.24

Storage

-0.24

Stored

-0.22

 stored

-0.22

 storage

-0.20

stored

-0.19

 Storage

-0.19

.storage

-0.19

_STORAGE

-0.18

POSITIVE LOGITS

.googleapis

0.28

house

0.22

 facility

0.20

 space

0.19

facility

0.19

 solutions

0.18

 facilities

0.18

uffix

0.17

HOUSE

0.17

.getItem

0.17

Activations Density 0.027%

references to storage facilities and related terms

No Comments

No Known Activations