INDEX

Explanations

mentions of television presenters or anchors

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

á»¥c

-0.16

kup

-0.15

ropa

-0.15

ladu

-0.14

IPA

-0.14

riculum

-0.14

 advanced

-0.14

 supervised

-0.13

orney

-0.13

POSITIVE LOGITS

 hosts

0.31

 host

0.29

hosts

0.28

 Host

0.27

HOST

0.27

Host

0.27

-host

0.26

anchor

0.25

 anchor

0.25

 hosting

0.23

Activations Density 0.118%

mentions of television presenters or anchors

No Comments

No Known Activations