INDEX

Explanations

references to guided tours and historical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 unread

-0.17

ãģķãĤī

-0.14

.getElementsByName

-0.14

-placeholder

-0.13

pectrum

-0.13

ł

-0.13

.idea

-0.13

idy

-0.13

mar

-0.13

inker

-0.13

POSITIVE LOGITS

 tour

0.77

 tours

0.75

 Tours

0.66

 Tour

0.63

tour

0.60

 TOUR

0.60

Tour

0.58

 toured

0.47

 touring

0.43

 guided

0.43

Activations Density 0.310%

references to guided tours and historical locations

No Comments

No Known Activations