INDEX

Explanations

references to storytelling techniques involving flashbacks and narrative framing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

DEST

-0.16

å½¦

-0.16

ahlen

-0.16

lep

-0.16

aspers

-0.15

anca

-0.15

ippi

-0.15

yclopedia

-0.15

osci

-0.14

daq

-0.14

POSITIVE LOGITS

0.14

biz

0.14

 Gilbert

0.14

enci

0.14

 Childhood

0.14

 Benson

0.14

æĭĽ

0.14

bi

0.14

gr

0.13

Activations Density 0.169%

references to storytelling techniques involving flashbacks and narrative framing

No Comments

No Known Activations