INDEX

Explanations

references to families and their emotional connections or experiences related to loss and trauma

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

egree

-0.16

ritz

-0.16

amarin

-0.15

gles

-0.15

(Seq

-0.14

Ã«l

-0.14

shall

-0.14

ostel

-0.14

TEE

-0.14

eum

-0.14

POSITIVE LOGITS

linger

0.15

 families

0.14

ached

0.14

Opr

0.14

ÐµÑĢÐ°Ð»ÑĮ

0.14

iped

0.14

ied

0.14

Ð½Ð¸ÐºÐ¾Ð²

0.14

irs

0.14

 LGPL

0.14

Activations Density 0.039%

references to families and their emotional connections or experiences related to loss and trauma

No Comments

No Known Activations