INDEX

Explanations

phrases related to political or organizational stances and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

bÃŃ

-0.15

æ¬

-0.14

iÅŁim

-0.14

ÅĻÃŃt

-0.13

ETY

-0.13

è¨

-0.13

roe

-0.13

ÙĪÙĦ

-0.13

Probe

-0.12

POSITIVE LOGITS

 position

0.80

 positions

0.67

 Position

0.64

position

0.63

Position

0.60

 POSITION

0.55

 Positions

0.54

positions

0.54

-position

0.53

_position

0.53

Activations Density 0.225%

phrases related to political or organizational stances and decisions

No Comments

No Known Activations