INDEX

Explanations

questions and details regarding the involvement and role of entities in developments and decisions

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

anova

-0.16

shan

-0.15

quo

-0.14

 lyon

-0.14

vertise

-0.14

 shit

-0.13

mouseenter

-0.13

Ø±ÙĪÛĮ

-0.13

quine

-0.13

ampaign

-0.13

POSITIVE LOGITS

AuthProvider

0.15

ogue

0.15

coni

0.15

ngle

0.15

ogle

0.14

åħ·ä½ĵ

0.14

avage

0.14

 ÑģÐ°Ð¼Ðµ

0.14

 Ð¾ÑĤÐ¿

0.14

Activations Density 0.157%

questions and details regarding the involvement and role of entities in developments and decisions

No Comments

No Known Activations