INDEX

Explanations

phrases related to argumentation and reasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

acos

-0.15

ukt

-0.14

cker

-0.14

 narr

-0.14

athon

-0.13

irl

-0.13

lov

-0.13

Kir

-0.13

 Gazette

-0.13

arResult

-0.13

POSITIVE LOGITS

lider

0.18

uce

0.14

istrat

0.14

ibi

0.14

ULE

0.14

hc

0.14

ohana

0.13

ê³ł

0.13

ogh

0.13

Activations Density 0.241%

phrases related to argumentation and reasoning

No Comments

No Known Activations