INDEX

Explanations

references to doors and openings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

avou

-0.15

iven

-0.15

vrier

-0.15

etting

-0.14

osy

-0.14

IVEN

-0.14

Ð¾Ð»Ð¾Ð²

-0.14

ongo

-0.13

agos

-0.13

.habbo

-0.13

POSITIVE LOGITS

Hed

0.15

ermal

0.14

 Cara

0.14

Open

0.14

 Norman

0.14

 instrumentation

0.13

 open

0.13

iras

0.13

 Open

0.13

atab

0.13

Activations Density 0.176%

references to doors and openings in various contexts

No Comments

No Known Activations