INDEX

Explanations

instances of specific names and phrases related to location and photography

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.15

;element

-0.15

rud

-0.14

 Wilson

-0.14

à¥ĩà¤ª

-0.14

assis

-0.14

oldt

-0.14

 Lange

-0.14

cru

-0.14

 Ð¿ÑĢÐ¾Ð³

-0.13

POSITIVE LOGITS

elig

0.16

 sebe

0.15

.pitch

0.15

ê¶Į

0.14

ECTOR

0.14

duto

0.14

LOAT

0.14

chip

0.14

Sab

0.14

andum

0.14

Activations Density 0.012%

instances of specific names and phrases related to location and photography

No Comments

No Known Activations