INDEX

Explanations

negative descriptors used to criticize people's behaviors and characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 precip

-0.15

Severity

-0.14

viz

-0.14

blink

-0.13

RowAt

-0.13

');?>↵

-0.13

stem

-0.13

ISC

-0.13

/Core

-0.13

POSITIVE LOGITS

 piece

0.26

Ass

0.25

dip

0.24

-piece

0.24

 pieces

0.24

mor

0.24

POS

0.24

Piece

0.24

cre

0.23

ass

0.23

Activations Density 0.380%

negative descriptors used to criticize people's behaviors and characteristics

No Comments

No Known Activations