INDEX

Explanations

instances of verbs indicating involvement or states of being, particularly in the context of community engagement and personal interests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÑĦÐ¸

-0.15

arc

-0.15

 overlooked

-0.14

ARC

-0.14

 neglected

-0.14

ÑĦÑĸ

-0.14

gren

-0.13

 segregated

-0.13

aa

-0.13

Ð»ÑĥÐ³Ð¸

-0.13

POSITIVE LOGITS

YRO

0.17

able

0.17

 Fauc

0.15

IAM

0.14

iam

0.14

entanyl

0.14

kin

0.14

ÅĻiv

0.14

aze

0.14

runner

0.14

Activations Density 0.290%

instances of verbs indicating involvement or states of being, particularly in the context of community engagement and personal interests

No Comments

No Known Activations