INDEX

Explanations

dates and chronological references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 occasional

-0.42

 occasionally

-0.42

 Occasionally

-0.36

Occ

-0.31

occ

-0.28

occ

-0.28

 occas

-0.28

 periodically

-0.26

 ocas

-0.25

 periodic

-0.24

POSITIVE LOGITS

 last

0.25

last

0.22

LAST

0.18

 LAST

0.18

(last

0.17

 letz

0.17

.last

0.17

 previous

0.17

 Ãºltimo

0.16

agma

0.15

Activations Density 0.190%

dates and chronological references

No Comments

No Known Activations