INDEX

Explanations

references to individuals and their roles, particularly in political or influential contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

es

-0.28

er

-0.21

eid

-0.19

eyn

-0.18

ea

-0.18

ease

-0.17

en

-0.16

oir

-0.16

erus

-0.16

erli

-0.16

POSITIVE LOGITS

ging

0.28

ÌĨ

0.24

ged

0.23

gers

0.23

gregator

0.22

gregation

0.21

gle

0.21

lio

0.20

ued

0.19

gy

0.19

Activations Density 0.043%

references to individuals and their roles, particularly in political or influential contexts

No Comments

No Known Activations