INDEX

Explanations

technical terminology and classifications related to scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð¸ÑĨ

-0.14

tml

-0.14

unar

-0.14

atile

-0.14

áº¹n

-0.14

eview

-0.14

dbo

-0.14

 VÅ¡ech

-0.14

iesz

-0.14

OTH

-0.14

POSITIVE LOGITS

eden

0.18

appa

0.16

enden

0.16

lit

0.15

 Moor

0.14

holm

0.14

 Accord

0.14

 Reese

0.14

mos

0.14

 Acceler

0.14

Activations Density 0.098%

technical terminology and classifications related to scientific research

No Comments

No Known Activations