INDEX

Explanations

numerical references and details about events or exhibitions

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

din

-0.16

nock

-0.15

 irrit

-0.14

zion

-0.14

å§ĭ

-0.14

wij

-0.14

ape

-0.14

errat

-0.14

apps

-0.14

onth

-0.13

POSITIVE LOGITS

istrate

0.15

LETTE

0.15

Ø¶

0.15

ê°ģ

0.14

 overl

0.14

ht

0.14

sme

0.14

teÅŁ

0.14

HeaderText

0.14

amilia

0.14

Activations Density 0.027%

numerical references and details about events or exhibitions

No Comments

No Known Activations