INDEX

Explanations

terms related to risks and issues in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ojis

-0.17

etch

-0.16

ecycle

-0.16

ãģ»ãģĨ

-0.15

abad

-0.14

ROP

-0.14

hle

-0.14

itter

-0.13

ahn

-0.13

oub

-0.13

POSITIVE LOGITS

 altogether

0.23

 Alto

0.17

 future

0.16

 overposting

0.15

 risk

0.15

 CAUSED

0.15

alto

0.15

ela

0.14

 HAPP

0.14

/false

0.14

Activations Density 0.164%

terms related to risks and issues in various contexts

No Comments

No Known Activations