INDEX

Explanations

information related to public speaking and media engagements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

chor

-0.15

orges

-0.15

eren

-0.14

mart

-0.14

lab

-0.14

 mart

-0.14

_CHOICES

-0.13

elfare

-0.13

Mig

-0.13

æĺŃ

-0.13

POSITIVE LOGITS

_nth

0.16

aber

0.16

ispens

0.15

onders

0.15

ubah

0.14

quan

0.14

ìĿ¸íĬ¸

0.14

unal

0.14

arrass

0.13

zimmer

0.13

Activations Density 0.130%

information related to public speaking and media engagements

No Comments

No Known Activations