INDEX

Explanations

references to deception or misrepresentation 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

vrier

-0.16

 THROW

-0.15

GroupBox

-0.15

ikk

-0.15

lias

-0.14

ç´Ļ

-0.14

peri

-0.14

æıĲåĩº

-0.14

wal

-0.13

 loose

-0.13

POSITIVE LOGITS

 facts

0.17

 reports

0.17

/false

0.16

Jar

0.15

 reporting

0.15

reports

0.15

 realities

0.14

facts

0.14

 about

0.14

ichert

0.14

Activations Density 0.097%

references to deception or misrepresentation in various contexts

No Comments

No Known Activations