INDEX

Explanations

terms related to medicinal benefits or effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Bite

-0.16

los

-0.15

VP

-0.14

pg

-0.14

 bite

-0.14

 Rossi

-0.14

sons

-0.14

Gh

-0.14

mod

-0.14

POSITIVE LOGITS

âĻª

0.17

.habbo

0.17

æĨ

0.15

orp

0.15

ancial

0.15

Bindable

0.15

 Cust

0.14

ogie

0.14

ipple

0.13

WebResponse

0.13

Activations Density 0.001%

terms related to medicinal benefits or effects

No Comments

No Known Activations