INDEX

Explanations

references to privacy and data protection policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

resco

-0.17

reek

-0.16

amina

-0.16

ÑĢÑĸÐ·

-0.16

 Ã¶den

-0.15

ÏĥÏĦÎ±Î½

-0.15

 Imports

-0.15

 meis

-0.14

anzi

-0.14

arkin

-0.14

POSITIVE LOGITS

 release

0.17

 nackte

0.16

 Release

0.16

gn

0.15

 trump

0.15

ando

0.15

 Pearl

0.15

oute

0.15

ts

0.15

Release

0.14

Activations Density 0.016%

references to privacy and data protection policies

No Comments

No Known Activations