INDEX

Explanations

terms related to child welfare and abuse issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

loi

-0.16

aksi

-0.16

ascade

-0.15

 akci

-0.15

ÐµÐ»Ðµ

-0.15

Ð¾Ð»Ð¾Ñģ

-0.15

éĺħè¯»æ¬¡æķ°

-0.14

iken

-0.14

_cv

-0.14

abei

-0.14

POSITIVE LOGITS

è»½

0.17

orie

0.16

omics

0.15

iniz

0.15

pole

0.15

 indirect

0.15

ongan

0.14

 Cent

0.14

itti

0.14

ken

0.14

Activations Density 0.029%

terms related to child welfare and abuse issues

No Comments

No Known Activations