INDEX

Explanations

references to the concept of credit, especially in the context of acknowledgment or responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ernaut

-0.18

itom

-0.17

awa

-0.16

 Brennan

-0.16

 Rover

-0.16

emailer

-0.16

ERSHEY

-0.16

erged

-0.15

samp

-0.15

 erot

-0.15

POSITIVE LOGITS

worth

0.30

worthy

0.30

ting

0.25

ric

0.21

ual

0.21

ted

0.20

ration

0.20

enance

0.18

ully

0.18

ably

0.17

Activations Density 0.022%

references to the concept of credit, especially in the context of acknowledgment or responsibility

No Comments

No Known Activations