INDEX

Explanations

attributes and characteristics of individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pie

-0.16

'gc

-0.15

imers

-0.14

dz

-0.14

readcr

-0.14

leans

-0.14

 Crud

-0.14

abis

-0.13

CU

-0.13

/module

-0.13

POSITIVE LOGITS

 Atlas

0.15

 atlas

0.15

 Pres

0.15

Ari

0.15

 Prot

0.14

tub

0.14

mb

0.14

eden

0.14

Activations Density 1.195%

attributes and characteristics of individuals or groups

No Comments

No Known Activations