INDEX

Explanations

references to dates, statistics, and financial performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

AGMA

-0.16

 neutral

-0.15

-neutral

-0.15

atitude

-0.14

 Chick

-0.14

ÑĢÐ°Ð»ÑĮ

-0.14

cea

-0.14

AUSE

-0.14

ÑĥÐ²Ð°

-0.13

á»ĵng

-0.13

POSITIVE LOGITS

efon

0.16

orst

0.15

reo

0.15

Kun

0.15

-Ta

0.15

istrar

0.14

Mathf

0.14

Bulletin

0.14

atel

0.14

strt

0.14

Activations Density 0.542%

references to dates, statistics, and financial performance metrics

No Comments

No Known Activations