INDEX

Explanations

references to trails and outdoor activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð°ÑĢÑħ

-0.16

struments

-0.14

ortal

-0.13

expiry

-0.13

.CG

-0.13

wares

-0.13

arehouse

-0.13

 Architects

-0.13

gence

-0.13

 ayar

-0.12

POSITIVE LOGITS

 trail

0.39

 trails

0.34

 Trail

0.33

Trail

0.31

trail

0.31

 Trails

0.30

ATV

0.25

 riders

0.24

 user

0.23

 rider

0.23

Activations Density 0.027%

references to trails and outdoor activities

No Comments

No Known Activations