INDEX

Explanations

terms that express emotional distress and suffering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

habit

-0.16

erg

-0.15

foy

-0.15

azen

-0.15

apos

-0.14

anie

-0.14

steam

-0.14

erten

-0.14

ãĤįãģĨ

-0.14

sworth

-0.14

POSITIVE LOGITS

ilk

0.16

 QByteArray

0.16

0.15

ormsg

0.15

ORIES

0.15

ingly

0.15

Ð½Ð¾Ð¿

0.15

0.14

å»º

0.14

 Dough

0.14

Activations Density 0.005%

terms that express emotional distress and suffering

No Comments

No Known Activations