INDEX

Explanations

references to historical architecture and renovations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ãģĦãģĭ

-0.15

ikhail

-0.15

dling

-0.15

é

-0.14

 poster

-0.14

asta

-0.14

-headed

-0.14

anke

-0.14

.slim

-0.14

 Benchmark

-0.13

POSITIVE LOGITS

sink

0.15

 Ling

0.15

chwitz

0.15

 Ø£Ø¬

0.14

ocities

0.14

bir

0.14

agas

0.14

pek

0.14

 Sang

0.14

ents

0.13

Activations Density 0.083%

references to historical architecture and renovations

No Comments

No Known Activations