INDEX

Explanations

mentions of governmental positions and related entities

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

 minimum

-0.21

Minimum

-0.20

 Minimum

-0.19

leigh

-0.18

_minimum

-0.18

minimum

-0.18

 mineral

-0.17

 Ð¼ÑĸÐ½ÑĸÐ¼

-0.17

eza

-0.17

 mÃŃnimo

-0.16

POSITIVE LOGITS

/max

0.31

ial

0.28

-max

0.20

atur

0.20

ipl

0.19

usc

0.18

imo

0.18

IAL

0.17

ogue

0.17

istic

0.17

Activations Density 0.039%

mentions of governmental positions and related entities

No Comments

No Known Activations