INDEX

Explanations

concepts related to emotional healing and processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ç¬

-0.16

ohon

-0.15

ajan

-0.15

attles

-0.14

igt

-0.14

à¤¿à¤¯à¤°

-0.14

vous

-0.14

ideon

-0.14

naire

-0.13

YRO

-0.13

POSITIVE LOGITS

 cath

0.16

 flower

0.15

 Anim

0.15

 ValueEventListener

0.15

 Flower

0.15

den

0.15

 Norm

0.14

ustum

0.14

-z

0.14

 limb

0.14

Activations Density 0.175%

concepts related to emotional healing and processing

No Comments

No Known Activations