INDEX

Explanations

references to the television show "Doctor Who" and its characters

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Chrysler

-0.15

dub

-0.14

fm

-0.14

IBUT

-0.14

mt

-0.14

dn

-0.13

 atas

-0.13

 cÃ¡

-0.13

awn

-0.13

POSITIVE LOGITS

Doctor

0.33

 Doctor

0.33

 Doctors

0.26

 regeneration

0.24

 doctor

0.24

 Companion

0.23

 Pert

0.23

 UNIT

0.22

 companions

0.21

BBC

0.21

Activations Density 0.047%

references to the television show "Doctor Who" and its characters

No Comments

No Known Activations