INDEX

Explanations

references to legal and judicial conditions and language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.15

ãĥĵãĥ¼

-0.15

TL

-0.15

-0.14

ilan

-0.14

iaux

-0.14

amment

-0.14

ohl

-0.14

.nlm

-0.14

-0.13

POSITIVE LOGITS

bsite

0.18

Ãºb

0.15

 barg

0.14

 Sach

0.14

Î´Îµ

0.14

burgh

0.14

 contemplated

0.14

chemes

0.14

ÑīÐ¾

0.13

Activations Density 0.477%

references to legal and judicial conditions and language

No Comments

No Known Activations