INDEX

Explanations

terms related to organizational structures and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 profitable

-0.14

Cog

-0.14

 benef

-0.14

 Simpson

-0.14

 silent

-0.14

onium

-0.13

umes

-0.13

 Rainbow

-0.13

veloper

-0.13

 Bowl

-0.13

POSITIVE LOGITS

 again

0.21

 Again

0.19

 weer

0.19

again

0.18

 novamente

0.18

Again

0.18

åĨį

0.17

ibri

0.16

asha

0.16

 lagi

0.16

Activations Density 0.006%

terms related to organizational structures and processes

No Comments

No Known Activations