INDEX

Explanations

discussions about rights, governance, and social justice issues

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

ourg

-0.17

urat

-0.15

Ģìŀ¥

-0.15

riad

-0.14

iques

-0.14

ãĤµãĤ¤

-0.14

averse

-0.14

ibold

-0.14

adesh

-0.14

assi

-0.14

POSITIVE LOGITS

 need

0.41

need

0.36

 Need

0.33

Need

0.31

 reck

0.28

_need

0.24

 care

0.24

aim

0.24

 NEED

0.23

 unjust

0.23

Activations Density 0.592%

discussions about rights, governance, and social justice issues

No Comments

No Known Activations