INDEX

Explanations

historical references related to significant figures and events

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

ARB

-0.16

imon

-0.15

Ãºp

-0.15

atego

-0.15

argon

-0.14

 ÑĤÐ²Ð°

-0.14

\db

-0.14

áº«

-0.14

ertest

-0.14

è³ŀ

-0.14

POSITIVE LOGITS

orna

0.18

sei

0.16

 sustain

0.16

 Bulls

0.14

orne

0.14

 sustained

0.14

aho

0.13

ocks

0.13

ennes

0.13

MAS

0.13

Activations Density 0.028%

historical references related to significant figures and events

No Comments

No Known Activations