INDEX

Explanations

terms related to child protection and discrimination policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Overflow

-0.17

-0.16

overflow

-0.16

pym

-0.15

meric

-0.15

äºķ

-0.15

Overflow

-0.14

 mate

-0.14

imentary

-0.14

rocket

-0.14

POSITIVE LOGITS

onu

0.17

child

0.15

childs

0.15

 triang

0.15

Saf

0.14

cas

0.14

Rin

0.14

 Manning

0.14

kola

0.14

jud

0.13

Activations Density 0.014%

terms related to child protection and discrimination policies

No Comments

No Known Activations