INDEX

Explanations

references to events occurring after significant incidents or crises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

cket

-0.15

cki

-0.15

erÃ§

-0.14

ativa

-0.14

.renderer

-0.14

ubo

-0.14

 Walsh

-0.14

nnen

-0.14

Expires

-0.14

xED

-0.13

POSITIVE LOGITS

lore

0.17

mer

0.16

nore

0.15

pon

0.15

.mousePosition

0.14

loat

0.14

bard

0.14

 Gang

0.14

peg

0.14

Tro

0.13

Activations Density 0.010%

references to events occurring after significant incidents or crises

No Comments

No Known Activations