INDEX

Explanations

references to podcasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 lyon

-0.15

uibModal

-0.15

åĩ

-0.15

ptal

-0.15

odesk

-0.15

uxt

-0.15

oothing

-0.14

quent

-0.14

æĿ

-0.14

oire

-0.14

POSITIVE LOGITS

casts

0.20

iatric

0.18

cast

0.18

 cast

0.17

UNK

0.17

ded

0.17

ium

0.17

ius

0.16

opsis

0.16

icip

0.15

Activations Density 0.016%

references to podcasts

No Comments

No Known Activations