INDEX

Explanations

terms related to active participation or involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

lant

-0.16

extr

-0.15

arian

-0.15

iegel

-0.14

 Singleton

-0.14

esModule

-0.14

AZY

-0.14

notated

-0.14

angelog

-0.14

assed

-0.14

POSITIVE LOGITS

0.18

 activities

0.15

eor

0.15

 Activities

0.15

in

0.15

illo

0.15

iven

0.15

apan

0.15

kin

0.14

quiv

0.14

Activations Density 0.028%

terms related to active participation or involvement

No Comments

No Known Activations