INDEX

Explanations

references to scientific publications and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

atak

-0.15

alars

-0.15

otor

-0.15

rame

-0.15

edor

-0.14

gri

-0.14

Hir

-0.14

 Ð¾Ð±Ð»Ð°

-0.14

 glory

-0.14

andom

-0.14

POSITIVE LOGITS

0.16

zed

0.16

enza

0.16

0.14

amm

0.14

ãĥ¼ãĥį

0.14

ws

0.14

imum

0.14

 DependencyProperty

0.13

Activations Density 0.050%

references to scientific publications and methodologies

No Comments

No Known Activations