INDEX

Explanations

references to rooms in various contexts, specifically focusing on their details and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ropy

-0.15

 chaud

-0.15

æĸ¹

-0.14

INTR

-0.14

 Curl

-0.14

.FLAG

-0.14

bben

-0.14

usher

-0.13

umbnail

-0.13

POSITIVE LOGITS

pez

0.17

sville

0.16

hattan

0.15

esktop

0.15

igan

0.15

runner

0.14

 lParam

0.14

rats

0.14

ong

0.14

æĸ¯çī¹

0.14

Activations Density 0.026%

references to rooms in various contexts, specifically focusing on their details and attributes

No Comments

No Known Activations