INDEX

Explanations

references to specific locations and events related to natural disasters or community impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Catalonia

-0.15

è±¡

-0.15

specifier

-0.14

hoo

-0.14

 Claw

-0.14

tu

-0.14

 Scarborough

-0.14

ont

-0.14

 McGill

-0.14

 Dubai

-0.13

POSITIVE LOGITS

 Somerset

0.17

 Bristol

0.17

upal

0.16

orio

0.16

hiba

0.16

lush

0.15

iper

0.15

ristol

0.14

ipple

0.14

Activations Density 0.069%

references to specific locations and events related to natural disasters or community impacts

No Comments

No Known Activations