INDEX

Explanations

elements related to geographical and cultural references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

$.

-0.14

vfs

-0.14

"."

-0.13

 EXEMPLARY

-0.12

ifact

-0.12

£¼

-0.12

edelta

-0.12

++.

-0.12

Â».

-0.12

ifetime

-0.12

POSITIVE LOGITS

 pronunciation

0.34

 pronounced

0.34

IPA

0.33

IPA

0.31

 listen

0.29

pron

0.29

 transl

0.28

 roman

0.27

lit

0.27

 sometimes

0.26

Activations Density 0.065%

elements related to geographical and cultural references

No Comments

No Known Activations